# Groq

> Fast LLM inference, OpenAI-compatible. Simple to integrate, easy to scale. Start building in minutes.

---

# Source: https://docs.groq.com/docs/api-reference#responses-streaming

# Source: https://docs.groq.com/docs/api-reference#responses-create

# Source: https://docs.groq.com/docs/api-reference#files-upload

# Source: https://docs.groq.com/docs/api-reference#chat-create

# Source: https://docs.groq.com/docs/api-reference#files-upload

# Source: https://docs.groq.com/docs/api-reference#batches

# Overview - GroqDocs

## Welcome

Fast LLM inference, OpenAI-compatible. Simple to integrate, easy to scale. Start building in minutes.

## External API Compatibility

- **gemma2-9b-it**
- **llama3-8b-8192**
- **llama3-70b-8192**
- **whisper-large-v3-turbo**
- **whisper-large-v3**
- **llama-guard-3-8b**
- **distil-whisper-large-v3-en**

## Chat Completion

- **Fast language models have gained significant attention in recent years due to their ability to process and generate human-like text quickly and efficiently. The importance of fast language models can be understood from their potential applications and benefits:**
  1. **Real-time Chatbots and Conversational Interfaces**: Fast language models enable the development of chatbots and conversational interfaces that can respond promptly to user queries, making them more engaging and useful.
  2. **Sentiment Analysis and Opinion Mining**: Fast language models can quickly analyze text data to identify sentiments, opinions, and emotions, allowing for improved customer service, market research, and opinion mining.
  3. **Language Translation and Localization**: Fast language models can quickly translate text between languages, facilitating global communication and enabling businesses to reach a broader audience.
  4. **Text Summarization and Generation**: Fast language models can summarize long documents or even generate new text on a given topic, improving information retrieval and processing efficiency.
  5. **Named Entity Recognition and Information Extraction**: Fast language models can rapidly recognize and extract specific entities, such as names, locations, and organizations, from unstructured text data.
  6. **Recommendation Systems**: Fast language models can analyze large amounts of text data to personalize product recommendations, improve customer experience, and increase sales.
  7. **Content Generation for Social Media**: Fast language models can quickly generate engaging content for social media platforms, helping businesses maintain a consistent online presence and increasing their online visibility.
  8. **Sentiment Analysis for Stock Market Analysis**: Fast language models can quickly analyze social media posts, news articles, and other text data to identify sentiment trends, enabling financial analysts to make more informed investment decisions.
  9. **Language Learning and Education**: Fast language models can provide instant feedback and adaptive language learning, making language education more effective and engaging.
  10. **Domain-Specific Knowledge Extraction**: Fast language models can quickly extract relevant information from vast amounts of text data, enabling domain experts to focus on high-level decision-making rather than manual information gathering.

The benefits of fast language models include:
- **Increased Efficiency**: Fast language models can process large amounts of text data quickly, reducing the time and effort required for tasks such as sentiment analysis, entity recognition, and text summarization.
- **Improved Accuracy**: Fast language models can analyze and learn from large datasets, leading to more accurate results and more informed decision-making.
- **Enhanced User Experience**: Fast language models can enable real-time interactions, personalized recommendations, and timely responses, improving the overall user experience.
- **Cost Savings**: Fast language models can automate many tasks, reducing the need for manual labor and minimizing costs associated with data processing and analysis.

In summary, fast language models have the potential to transform various industries and applications by providing fast, accurate, and efficient language processing capabilities.

## Chat Completion Request

- **Description**: A document that can be referenced by the model while generating responses.
- **Properties**:
  - **id**: Optional unique identifier that can be used for citations in responses.
  - **source**: Document containing the text content.

## Chat Completion Response

- **Description**: A chat completion message generated by the model.
- **Properties**:
  - **annotations**: A list of annotations providing citations and references for the content in the message.
  - **content**: The contents of the message.
  - **executed_tools**: Information about the tools that were executed during the chat completion for compound AI systems.
  - **function_call**: Controls which (if any) function is called by the model.
  - **reasoning**: The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
  - **role**: The role of the messages author, in this case `assistant`.
  - **tool_calls**: The tool calls generated by the model, such as function calls.

## Chat Completion Role

- **Description**: The role of the author of a message.
- **Values**:
  - `system`
  - `user`
  - `assistant`
  - `tool`
  - `developer`

## Chat Completion Stream

- **Description**: A chat completion delta generated by streamed model responses.
- **Properties**:
  - **annotations**: A list of annotations providing citations and references for the content in the message.
  - **content**: The contents of the chunk message.
  - **executed_tools**: Information about the tools that were executed during the chunk.
  - **reasoning**: The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
  - **role**: The role of the author of this message.
  - **tool_calls**: The tools that were available to the model.

## Chat Completion Token Logprob

- **Description**: A list of tokens with log probability information.
- **Properties**:
  - **bytes**: A list of integers representing the UTF-8 bytes representation of the token.
  - **logprob**: The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely.

## Chat Completion Tool

- **Description**: Describes a tool that the model may generate JSON inputs for.
- **Properties**:
  - **name**: The name of the function to be called.
  - **parameters**: A JSON schema describing the function's input parameters.

## Chat Completion Response Message

- **Description**: A message input to the model with a role indicating instruction following hierarchy.
- **Properties**:
  - **content**: A list of one or many input content items.
  - **role**: The role of the message input.
  - **status**: The status of the message.
  - **type**: The type of the message input.

## Chat Completion Response FileCitation

- **Description**: A citation to a file.
- **Properties**:
  - **file_id**: The ID of the file.
  - **index**: The index of the citation in the text.
  - **type**: The type of the annotation. Always `file_citation`.
  - **url**: The URL of the file.

## Chat Completion Response TextCitation

- **Description**: A citation for a web resource.
- **Properties**:
  - **end_index**: The character index in the URL citation in the message.
  - **start_index**: The character index in the URL citation in the message.
  - **title**: The title of the web resource.
  - **type**: The type of the annotation. Always `url_citation`.
  - **url**: The URL of the web resource.

## Chat Completion Usage Breakdown

- **Description**: Usage statistics for compound AI completion requests.
- **Properties**:
  - **models**: List of models used in the request and their individual usage statistics.
  - **type**: The type of the response format being defined. Always `list`.

## Chat Completion StreamResponseDelta

- **Description**: A chat completion delta generated by streamed model responses.
- **Properties**:
  - **annotations**: A list of annotations providing citations and references for the content in the message.
  - **content**: The contents of the chunk message.
  - **executed_tools**: Information about the tools that were executed during the chunk.
  - **reasoning**: The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
  - **role**: The role of the author of this message.
  - **tool_calls**: The tools that were available to the model.

## Chat Completion Response Message

- **Description**: A message input to the model with explicit type field.
- **Properties**:
  - **content**: A list of one or many input content items.
  - **role**: The role of the message input.
  - **status**: The status of item. Populated when items are returned via API.
  - **type**: The type of the message input. Always set to `message`.

## Chat Completion Response TextContent

- **Description**: A text input to the model.
- **Properties**:
  - **text**: The text input to the model.
  - **type**: The type of the input item. Always `input_text`.

## Chat Completion Response FileContent

- **Description**: A file input to the model.
- **Properties**:
  - **bytes**: The size of the file, in bytes.
  - **created_at**: The Unix timestamp (in seconds) for when the file was created.
  - **filename**: The name of the file.
  - **id**: The file identifier, which can be referenced in the API endpoints.
  - **object**: The object type, which is always `file`.
  - **purpose**: The intended purpose of the file. Supported values are `batch` and `batch_output`.

## Chat Completion Response JsonSchema

- **Description**: JSON schema response format. Used to generate structured JSON responses.
- **Properties**:
  - **type**: The type of response format being defined. Always `json_object`.
  - **schema**: The schema for the response format, described as a JSON Schema object.
  - **strict**: Whether to enable strict schema adherence when generating the output. Only a subset of JSON Schema is supported when `strict` is `true`.

## Chat Completion Response TextContent

- **Description**: A text output from the model.
- **Properties**:
  - **annotations**: The annotations of the text output.
  - **logprobs**: Log probability information for the output.
  - **text**: The text output from the model.
  - **type**: The type of the output text. Always `output_text`.

## Chat Completion Response FunctionCall

- **Description**: A function call generated by the model.
- **Properties**:
  - **arguments**: A JSON string of the arguments to pass to the function.
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call.
  - **name**: The name of the function to call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Response FunctionCallOutput

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Response EasyInputMessage

- **Description**: A message input to the model with a role indicating instruction following hierarchy.
- **Properties**:
  - **content**: A list of one or many input content items.
  - **role**: The role of the message input.
  - **status**: The status of item. Populated when items are returned via API.
  - **type**: The type of the message input. Always set to `message`.

## Chat Completion Response FileCitation

- **Description**: A citation to a file.
- **Properties**:
  - **end_index**: The character index in the URL citation in the message.
  - **start_index**: The character index in the URL citation in the message.
  - **title**: The title of the file.
  - **type**: The type of the annotation. Always `file_citation`.
  - **url**: The URL of the file.

## Chat Completion Response Usage

- **Description**: Usage statistics for the response request.
- **Properties**:
  - **input_tokens**: Number of tokens in the input.
  - **input_tokens_details**: Breakdown of input tokens.
  - **output_tokens**: Number of tokens in the generated output.
  - **output_tokens_details**: Breakdown of output tokens.
  - **total_tokens**: Total number of tokens used in the request (input + output).

## Text Response Format JsonSchema

- **Description**: JSON Schema response format. Used to generate structured JSON responses.
- **Properties**:
  - **description**: A description of what the response format is for, used by the model to determine how to respond in the format.
  - **name**: The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
  - **schema**: The schema for the response format, described as a JSON Schema object.
  - **strict**: Whether to enable strict schema adherence when generating the output. Only a subset of JSON Schema is supported when `strict` is `true`.

## TranscriptionSegment

- **Description**: A segment of the transcribed text.
- **Properties**:
  - **audio_text**: Transcribed text for the entire chunk.
  - **avg_logprob**: Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.
  - **chunk_end**: End chunk timestamp.
  - **chunk_start**: Start chunk timestamp.
  - **compression_ratio**: Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.
  - **end**: End time of the segment in seconds.
  - **id**: Unique identifier of the segment.
  - **no_speech_prob**: Probability of no speech in the segment. If the value is higher than 1.0 and the `avg_logprob` is below -1, consider this segment silent.
  - **seek**: Seek offset of the segment.
  - **start**: Start time of the segment in seconds.
  - **temperature**: Temperature parameter used for generating the segment.
  - **text**: Text content of the segment.
  - **token_scores**: Token-level scores.
  - **tokens**: Array of token IDs for the text content.

## XGroq

- **Description**: Groq-specific metadata for streaming responses.
- **Properties**:
  - **debug**: An array of debug data.
  - **error**: An error string indicating why a stream was stopped early.
  - **id**: A groq request ID which can be used to refer to a specific request to groq support.
  - **seed**: The seed used for the request. See the seed property on CreateChatCompletionRequest for more details.
  - **usage**: Additional Groq-specific usage metrics (hardware cache statistics).

## XGroqNonStreaming

- **Description**: Groq-specific metadata for non-streaming chat completion responses.
- **Properties**:
  - **debug**: An array of debug data.
  - **id**: A groq request ID which can be used to refer to a specific request to groq support.
  - **seed**: The seed used for the request. See the seed property on CreateChatCompletionRequest for more details.
  - **usage**: Additional Groq-specific usage metrics (hardware cache statistics).

## GroqCloud API Specification

- **Contact**: Support
- **Description**: Specification of the Groq cloud API
- **Terms of Service**: https://groq.com/terms-of-use/
- **Title**: GroqCloud API
- **Version**: 2.1

## Groq Support

- **Email**: support@groq.com
- **Name**: Groq Support

## Groq API Endpoint

- **URL**: https://api.groq.com

## Groq API Request Example

- **curl**: curl https://api.groq.com/openai/v1/audio/speech -H "Authorization: Bearer $GROQ_API_KEY" -H "Content-Type: application/json" -d '{ "model": "playai-tts", "input": "I love building and shipping new features for our users!", "voice": "Fritz-PlayAI", "response_format": "wav" }'

- **js**: import fs from "fs"; import path from "path"; import Groq from 'groq-sdk'; const groq = new Groq({ apiKey: process.env.GROQ_API_KEY }); const speechFilePath = "speech.wav"; const model = "playai-tts"; const voice = "Fritz-PlayAI"; const text = "I love building and shipping new features for our users!"; const responseFormat = "wav"; async function main() { const response = await groq.audio.speech.create({ model: model, voice: voice, input: text, response_format: responseFormat }); const buffer = Buffer.from(await response.arrayBuffer()); await fs.promises.writeFile(speechFilePath, buffer); } main();

- **py**: import os from groq import Groq client = Groq(api_key=os.environ.get("GROQ_API_KEY")) speech_file_path = "speech.wav" model = "playai-tts" voice = "Fritz-PlayAI" text = "I love building and shipping new features for our users!" response_format = "wav" response = client.audio.speech.create( model=model, voice=voice, input=text, response_format=response_format ) response.write_to_file(speech_file_path)

## Groq API Response Example

- **response**: { "text": "Your transcribed text appears here...", "x_groq": { "id": "req_unique_id" } }

## Groq API Response Format

- **JSON Schema**: JSON Schema response format. Used to generate structured JSON responses.
- **Properties**: { "type": "object", "properties": { "description": { "type": "string", "description": "A description of what the response format is for, used by the model to determine how to respond in the format." }, "name": { "type": "string", "description": "The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64." }, "schema": { "type": "object", "description": "The schema for the response format, described as a JSON Schema object." }, "strict": { "type": "boolean", "description": "Whether to enable strict schema adherence when generating the output." } } }

## Groq API Response Format Text

- **Description**: A text output from the model.
- **Properties**: { "annotations": { "type": "array", "items": { "type": "string" } }, "logprobs": { "type": "array", "items": { "type": "string" } }, "text": { "type": "string" }, "type": { "type": "string", "description": "The type of the output text. Always `output_text`." } }

## Groq API Response Format TextContent

- **Description**: A text input to the model.
- **Properties**: { "text": { "type": "string" }, "type": { "type": "string", "description": "The type of the input item. Always `input_text`." } }

## Groq API Response FileContent

- **Description**: A file input to the model.
- **Properties**: { "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileCitation

- **Description**: A citation to a file.
- **Properties**: { "end_index": { "type": "integer" }, "start_index": { "type": "integer" }, "title": { "type": "string" }, "type": { "type": "string", "description": "The type of the annotation. Always `file_citation`." }, "url": { "type": "string" } }

## Groq API Response Usage Breakdown

- **Description**: Usage statistics for the response request.
- **Properties**: { "input_tokens": { "type": "integer" }, "input_tokens_details": { "type": "object", "properties": { "cached_tokens": { "type": "integer" }, "reasoning_tokens": { "type": "integer" } } }, "output_tokens": { "type": "integer" }, "output_tokens_details": { "type": "object", "properties": { "cached_tokens": { "type": "integer" }, "reasoning_tokens": { "type": "integer" } } }, "total_tokens": { "type": "integer" } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at": { "type": "integer" }, "filename": { "type": "string" }, "purpose": { "type": "string", "description": "The purpose of the file." } }

## Groq API Response FileContent

- **Description**: A file object.
- **Properties**: { "id": { "type": "string" }, "object": { "type": "string", "description": "The object type, which is always `file`." }, "bytes": { "type": "integer" }, "created_at

---

# Source: https://docs.groq.com/docs/batch

# Overview - GroqDocs

## Welcome

Fast LLM inference, OpenAI-compatible. Simple to integrate, easy to scale. Start building in minutes.

## External API Compatibility

- **gemma2-9b-it**
- **llama3-8b-8192**
- **llama3-70b-8192**
- **whisper-large-v3-turbo**
- **whisper-large-v3**
- **llama-guard-3-8b**
- **distil-whisper-large-v3-en**

## Chat Completion

- **Fast language models have gained significant attention in recent years due to their ability to process and generate human-like text quickly and efficiently. The importance of fast language models can be understood from their potential applications and benefits:**
  1. **Real-time Chatbots and Conversational Interfaces**: Fast language models enable the development of chatbots and conversational interfaces that can respond promptly to user queries, making them more engaging and useful.
  2. **Sentiment Analysis and Opinion Mining**: Fast language models can quickly analyze text data to identify sentiments, opinions, and emotions, allowing for improved customer service, market research, and opinion mining.
  3. **Language Translation and Localization**: Fast language models can quickly translate text between languages, facilitating global communication and enabling businesses to reach a broader audience.
  4. **Text Summarization and Generation**: Fast language models can summarize long documents or even generate new text on a given topic, improving information retrieval and processing efficiency.
  5. **Named Entity Recognition and Information Extraction**: Fast language models can rapidly recognize and extract specific entities, such as names, locations, and organizations, from unstructured text data.
  6. **Recommendation Systems**: Fast language models can analyze large amounts of text data to personalize product recommendations, improve customer experience, and increase sales.
  7. **Content Generation for Social Media**: Fast language models can quickly generate engaging content for social media platforms, helping businesses maintain a consistent online presence and increasing their online visibility.
  8. **Sentiment Analysis for Stock Market Analysis**: Fast language models can quickly analyze social media posts, news articles, and other text data to identify sentiment trends, enabling financial analysts to make more informed investment decisions.
  9. **Language Learning and Education**: Fast language models can provide instant feedback and adaptive language learning, making language education more effective and engaging.
  10. **Domain-Specific Knowledge Extraction**: Fast language models can quickly extract relevant information from vast amounts of text data, enabling domain experts to focus on high-level decision-making rather than manual information gathering.

The benefits of fast language models include:
- **Increased Efficiency**: Fast language models can process large amounts of text data quickly, reducing the time and effort required for tasks such as sentiment analysis, entity recognition, and text summarization.
- **Improved Accuracy**: Fast language models can analyze and learn from large datasets, leading to more accurate results and more informed decision-making.
- **Enhanced User Experience**: Fast language models can enable real-time interactions, personalized recommendations, and timely responses, improving the overall user experience.
- **Cost Savings**: Fast language models can automate many tasks, reducing the need for manual labor and minimizing costs associated with data processing and analysis.

In summary, fast language models have the potential to transform various industries and applications by providing fast, accurate, and efficient language processing capabilities.

## Chat Completion Request

- **Description**: A document that can be referenced by the model while generating responses.
- **Properties**:
  - **id**: Optional unique identifier that can be used for citations in responses.
  - **source**: Document containing the text content.

## Chat Completion Response

- **Description**: A chat completion message generated by the model.
- **Properties**:
  - **annotations**: A list of annotations providing citations and references for the content in the message.
  - **content**: The contents of the message.
  - **executed_tools**: Information about the tools that were executed during the chat completion for compound AI systems.
  - **function_call**: Controls which (if any) function is called by the model.
  - **reasoning**: The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
  - **role**: The role of the messages author, in this case `assistant`.
  - **tool_calls**: The tool calls generated by the model, such as function calls.

## Chat Completion Role

- **Description**: The role of the author of a message.
- **Values**:
  - `system`
  - `user`
  - `assistant`
  - `tool`
  - `function`

## Chat Completion Stream

- **Description**: A chat completion delta generated by streamed model responses.
- **Properties**:
  - **annotations**: A list of annotations providing citations and references for the content in the message.
  - **content**: The contents of the chunk message.
  - **executed_tools**: Information about the tools that were executed during the chunk.
  - **reasoning**: The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
  - **role**: The role of the author of this message.
  - **tool_calls**: The tools that were available to the model.

## Chat Completion Token Logprob

- **Description**: A list of tokens with log probability information.
- **Properties**:
  - **bytes**: A list of integers representing the UTF-8 bytes representation of the token.
  - **logprob**: The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely.

## Chat Completion Tool

- **Description**: Describes a tool that the model may generate JSON inputs for.
- **Properties**:
  - **name**: The name of the function to be called.
  - **parameters**: A JSON schema describing the function's input parameters.

## Chat Completion Response Message

- **Description**: A message input to the model with a role indicating instruction following hierarchy.
- **Properties**:
  - **content**: A list of one or many input content items.
  - **role**: The role of the message input.
  - **status**: The status of the message.
  - **type**: The type of the message input.

## Chat Completion Response FileCitation

- **Description**: A citation to a file.
- **Properties**:
  - **file_id**: The ID of the file.
  - **index**: The index of the citation in the text.
  - **type**: The type of the annotation. Always `file_citation`.
  - **url**: The URL of the file.

## Chat Completion Response TextCitation

- **Description**: A citation for a web resource.
- **Properties**:
  - **end_index**: The character index in the URL citation in the message.
  - **start_index**: The character index in the URL citation in the message.
  - **title**: The title of the web resource.
  - **type**: The type of the annotation. Always `url_citation`.
  - **url**: The URL of the web resource.

## Chat Completion Usage Breakdown

- **Description**: Usage statistics for compound AI completion requests.
- **Properties**:
  - **models**: List of models used in the request and their individual usage statistics.
  - **type**: The type of the response format being defined. Always `json_object`.

## Chat Completion Response

- **Description**: Represents a response returned by model, based on the provided input.
- **Properties**:
  - **background**: Whether the response was generated in the background.
  - **created_at**: The Unix timestamp (in seconds) of when the response was created.
  - **error**: An error object if the response failed.
  - **param**: Optional parameter to guide the model's style or continue a previous audio segment.
  - **message**: The system message used for the response.
  - **max_output_tokens**: An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
  - **metadata**: Custom key-value pairs for storing additional information. Maximum of 16 pairs.
  - **model**: ID of the model to use.
  - **object**: The object type, which is always `chat.completion`.
  - **usage**: Usage information for the request.
  - **previous_response_id**: Not supported. Always null.
  - **reasoning**: Configuration options for [models that support reasoning](https://console.groq.com/docs/reasoning).
  - **response_format**: An object specifying the format that the model must output.
  - **stream**: Enable streaming mode to receive response data as server-sent events.
  - **temperature**: Controls randomness in the response generation.
  - **tool_choice**: Controls which (if any) tool is called by the model.
  - **tools**: List of tools available to the model.
  - **top_logprobs**: The number of top log probabilities returned.
  - **top_p**: The nucleus sampling parameter used.
  - **truncation**: The truncation strategy used.
  - **usage_breakdown**: Detailed usage breakdown by model when multiple models are used in the request for compound AI systems.
  - **user**: Optional identifier for tracking end-user requests.

## Chat Completion Stream Response

- **Description**: Represents a streamed chunk of a chat completion response returned by model, based on the provided input.
- **Properties**:
  - **annotations**: A list of annotations providing citations and references for the content in the message.
  - **content**: The contents of the chunk message.
  - **executed_tools**: Information about the tools that were executed during the chunk.
  - **reasoning**: Configuration options for [models that support reasoning](https://console.groq.com/docs/reasoning).
  - **role**: The role of the author of this message.
  - **tool_calls**: The tools that were available to the model.

## Chat Completion Response Message

- **Description**: A message input to the model with explicit type field.
- **Properties**:
  - **content**: A list of one or many input content items.
  - **role**: The role of the message input.
  - **status**: The status of item. Populated when items are returned via API.
  - **type**: The type of the message input.

## Chat Completion Response TextCitation

- **Description**: A text input to the model.
- **Properties**:
  - **text**: The text input to the model.
  - **type**: The type of the input item. Always `input_text`.

## Chat Completion Response FileCitation

- **Description**: A citation to a file.
- **Properties**:
  - **file_id**: The ID of the file.
  - **index**: The index of the citation in the text.
  - **type**: The type of the annotation. Always `file_citation`.
  - **url**: The URL of the file.

## Chat Completion Response TextContent

- **Description**: A text output from the model.
- **Properties**:
  - **annotations**: The annotations of the text output.
  - **logprobs**: Log probability information for the output.
  - **text**: The text output from the model.
  - **type**: The type of the output text. Always `output_text`.

## Chat Completion Response FunctionCall

- **Description**: A function call generated by the model.
- **Properties**:
  - **arguments**: A JSON string of the arguments to pass to the function.
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call.
  - **name**: The name of the function to call.
  - **status**: The status of the item. Populated when items are returned via API.
  - **type**: The type of the function call. Always `function_call`.

## Chat Completion Response FunctionCallOutput

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Response EasyInputMessage

- **Description**: A message input to the model with explicit type field.
- **Properties**:
  - **content**: A list of one or many input content items.
  - **role**: The role of the message input.
  - **status**: The status of item. Populated when items are returned via API.
  - **type**: The type of the message input. Always `message`.

## Chat Completion Response FileCitation

- **Description**: A citation to a file.
- **Properties**:
  - **end_index**: The character index in the URL citation in the message.
  - **start_index**: The character index in the URL citation in the message.
  - **title**: The title of the file.
  - **type**: The type of the annotation. Always `url_citation`.
  - **url**: The URL of the file.

## Chat Completion Response Usage

- **Description**: Usage statistics for the response request.
- **Properties**:
  - **input_tokens**: Number of tokens in the input.
  - **input_tokens_details**: Breakdown of input tokens.
  - **output_tokens**: Number of tokens in the generated output.
  - **output_tokens_details**: Breakdown of output tokens.
  - **total_tokens**: Total number of tokens used in the request (input + output).

## Text Response Format JsonSchema

- **Description**: JSON Schema response format. Used to generate structured JSON responses.
- **Properties**:
  - **description**: A description of what the response format is for, used by the model to determine how to respond in the format.
  - **name**: The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
  - **schema**: The schema for the response format, described as a JSON Schema object.
  - **strict**: Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the `schema` field. Only a subset of JSON Schema is supported when `strict` is `true`.

## Transcription Segment

- **Description**: A segment of the transcribed text.
- **Properties**:
  - **audio_text**: Transcribed text for the entire chunk.
  - **avg_logprob**: Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.
  - **chunk_end**: End chunk timestamp.
  - **chunk_start**: Start chunk timestamp.
  - **compression_ratio**: Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.
  - **end**: End time of the segment in seconds.
  - **id**: Unique identifier of the segment.
  - **no_speech_prob**: Probability of no speech in the segment. If the value is higher than 1.0 and the `avg_logprob` is below -1, consider this segment silent.
  - **seek**: Seek offset of the segment.
  - **start**: Start time of the segment in seconds.
  - **temperature**: Temperature parameter used for generating the segment.
  - **text**: Text content of the segment.
  - **token_scores**: Token-level scores.
  - **tokens**: Array of token IDs for the text content.

## XGroq

- **Description**: Groq-specific metadata for streaming responses.
- **Properties**:
  - **debug**: Optional Groq request ID which can be used to refer to a specific request to groq support.
  - **error**: An error string indicating why a stream was stopped early.
  - **id**: A groq request ID which can be used to refer to a specific request to groq support.
  - **seed**: The seed used for the request. See the seed property on CreateChatCompletionRequest for more details.
  - **usage**: Additional Groq-specific usage metrics (hardware cache statistics).

## XGroq NonStreaming

- **Description**: Groq-specific metadata for non-streaming chat completion responses.
- **Properties**:
  - **debug**: Optional Groq request ID which can be used to refer to a specific request to groq support.
  - **id**: A groq request ID which can be used to refer to a specific request to groq support.
  - **seed**: The seed used for the request. See the seed property on CreateChatCompletionRequest for more details.
  - **usage**: Additional Groq-specific usage metrics (hardware cache statistics).

## Groq Cloud API Specification

- **Contact**: support@groq.com
- **Description**: Specification of the Groq cloud API
- **Terms of Service**: https://groq.com/terms-of-use/
- **Title**: GroqCloud API
- **Version**: 2.1

## Groq Support

- **Email**: support@groq.com
- **Name**: Groq Support

## Groq API Endpoint

- **URL**: https://api.groq.com

## Groq API Version

- **Version**: 2.1

## Groq API Schema

- **API Key**: api_key
- **Content Type**: application/json
- **Schema**: $ref: #/components/schemas/CreateChatCompletionRequest

## Groq API Request

- **Description**: The input prompt and parameters
- **Required**: true

## Groq API Response

- **Description**: OK

## Groq API Error

- **Description**: OK

## Groq API Example Request

- **Curl**: curl https://api.groq.com/openai/v1/audio/speech -H "Authorization: Bearer $GROQ_API_KEY" -H "Content-Type: application/json" -d '{ "model": "playai-tts", "input": "I love building and shipping new features for our users!", "voice": "Fritz-PlayAI", "response_format": "wav" }'

## Groq API Example Response

- **JSON**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Text**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your transcribed text appears here...", "x_groq": {"id": "req_unique_id"}}
- **Response**: {"text": "Your translated text appears here...", "x_groq": {"id":

---

# Source: https://docs.groq.com/docs/guides/embeddings

# Overview - GroqDocs

## Welcome

Fast LLM inference, OpenAI-compatible. Simple to integrate, easy to scale. Start building in minutes.

## External API Compatibility

- **gemma2-9b-it**
- **llama3-8b-8192**
- **llama3-70b-8192**
- **whisper-large-v3-turbo**
- **whisper-large-v3**
- **llama-guard-3-8b**
- **distil-whisper-large-v3-en**

## Chat Completion

- **Fast language models have gained significant attention in recent years due to their ability to process and generate human-like text quickly and efficiently. The importance of fast language models can be understood from their potential applications and benefits:**
  1. **Real-time Chatbots and Conversational Interfaces**: Fast language models enable the development of chatbots and conversational interfaces that can respond promptly to user queries, making them more engaging and useful.
  2. **Sentiment Analysis and Opinion Mining**: Fast language models can quickly analyze text data to identify sentiments, opinions, and emotions, allowing for improved customer service, market research, and opinion mining.
  3. **Language Translation and Localization**: Fast language models can quickly translate text between languages, facilitating global communication and enabling businesses to reach a broader audience.
  4. **Text Summarization and Generation**: Fast language models can summarize long documents or even generate new text on a given topic, improving information retrieval and processing efficiency.
  5. **Named Entity Recognition and Information Extraction**: Fast language models can rapidly recognize and extract specific entities, such as names, locations, and organizations, from unstructured text data.
  6. **Recommendation Systems**: Fast language models can analyze large amounts of text data to personalize product recommendations, improve customer experience, and increase sales.
  7. **Content Generation for Social Media**: Fast language models can quickly generate engaging content for social media platforms, helping businesses maintain a consistent online presence and increasing their online visibility.
  8. **Sentiment Analysis for Stock Market Analysis**: Fast language models can quickly analyze social media posts, news articles, and other text data to identify sentiment trends, enabling financial analysts to make more informed investment decisions.
  9. **Language Learning and Education**: Fast language models can provide instant feedback and adaptive language learning, making language education more effective and engaging.
  10. **Domain-Specific Knowledge Extraction**: Fast language models can quickly extract relevant information from vast amounts of text data, enabling domain experts to focus on high-level decision-making rather than manual information gathering.

The benefits of fast language models include:
- **Increased Efficiency**: Fast language models can process large amounts of text data quickly, reducing the time and effort required for tasks such as sentiment analysis, entity recognition, and text summarization.
- **Improved Accuracy**: Fast language models can analyze and learn from large datasets, leading to more accurate results and more informed decision-making.
- **Enhanced User Experience**: Fast language models can enable real-time interactions, personalized recommendations, and timely responses, improving the overall user experience.
- **Cost Savings**: Fast language models can automate many tasks, reducing the need for manual labor and minimizing costs associated with data processing and analysis.

In summary, fast language models have the potential to transform various industries and applications by providing fast, accurate, and efficient language processing capabilities.

## Chat Completion Request

- **Description**: A document that can be referenced by the model while generating responses.
- **Properties**:
  - **id**: Optional unique identifier that can be used for citations in responses.
  - **source**: The document containing the text to be referenced by the model.

## Chat Completion Response

- **Description**: A chat completion message generated by the model.
- **Properties**:
  - **annotations**: A list of annotations providing citations and references for the content in the message.
  - **content**: The contents of the message.
  - **executed_tools**: Information about the tools that were executed during the chat completion for compound AI systems.
  - **function_call**: Controls which (if any) function is called by the model.
  - **reasoning**: The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
  - **role**: The role of the messages author, in this case `assistant`.
  - **tool_calls**: The tool calls generated by the model, such as function calls.

## Chat Completion Role

- **Description**: The role of the author of a message.
- **Values**:
  - `system`
  - `user`
  - `assistant`
  - `tool`
  - `function`

## Chat Completion Stream

- **Description**: A chat completion delta generated by streamed model responses.
- **Properties**:
  - **annotations**: A list of annotations providing citations and references for the content in the message.
  - **content**: The contents of the chunk message.
  - **executed_tools**: Information about the tools that were executed during the chunk.
  - **reasoning**: The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
  - **role**: The role of the author of this message.
  - **tool_calls**: The tools that were available to the model.

## Chat Completion Token Logprob

- **Description**: A list of tokens with log probability information.
- **Properties**:
  - **bytes**: A list of integers representing the UTF-8 bytes representation of the token.
  - **logprob**: The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely.

## Chat Completion Tool

- **Description**: Describes a tool that can be used by the model.
- **Properties**:
  - **allowed_tools**: A list of tool names to allow from the MCP server. If specified, only these tools will be exposed to the model. If empty or not specified, all discovered tools will be available.
  - **function**: Custom model to use for answering.
  - **reasoning_model**: Custom model to use for reasoning.
  - **parameters**: Configuration options for tools available to Compound.
  - **type**: Type is always `function`.

## Chat Completion Function Call

- **Description**: A function call generated by the model.
- **Properties**:
  - **arguments**: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call.
  - **name**: The name of the function to call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Chunk

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Calls

- **Description**: The tool calls generated by the model, such as function calls.

## Chat Completion Message Tool Call Chunk

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Currently, only `function` is supported.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Message Tool Call

- **Description**: Controls which (if any) tool is called by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of

---

# Source: https://docs.groq.com/docs/guides/speech-to-text/prompting

# Overview - GroqDocs

## Welcome

Fast LLM inference, OpenAI-compatible. Simple to integrate, easy to scale. Start building in minutes.

## External API Compatibility

- **gemma2-9b-it**
- **llama3-8b-8192**
- **llama3-70b-8192**
- **whisper-large-v3-turbo**
- **whisper-large-v3**
- **llama-guard-3-8b**
- **distil-whisper-large-v3-en**

## Chat Completion

- **Fast language models have gained significant attention in recent years due to their ability to process and generate human-like text quickly and efficiently. The importance of fast language models can be understood from their potential applications and benefits:**
  1. **Real-time Chatbots and Conversational Interfaces**: Fast language models enable the development of chatbots and conversational interfaces that can respond promptly to user queries, making them more engaging and useful.
  2. **Sentiment Analysis and Opinion Mining**: Fast language models can quickly analyze text data to identify sentiments, opinions, and emotions, allowing for improved customer service, market research, and opinion mining.
  3. **Language Translation and Localization**: Fast language models can quickly translate text between languages, facilitating global communication and enabling businesses to reach a broader audience.
  4. **Text Summarization and Generation**: Fast language models can summarize long documents or even generate new text on a given topic, improving information retrieval and processing efficiency.
  5. **Named Entity Recognition and Information Extraction**: Fast language models can rapidly recognize and extract specific entities, such as names, locations, and organizations, from unstructured text data.
  6. **Recommendation Systems**: Fast language models can analyze large amounts of text data to personalize product recommendations, improve customer experience, and increase sales.
  7. **Content Generation for Social Media**: Fast language models can quickly generate engaging content for social media platforms, helping businesses maintain a consistent online presence and increasing their online visibility.
  8. **Sentiment Analysis for Stock Market Analysis**: Fast language models can quickly analyze social media posts, news articles, and other text data to identify sentiment trends, enabling financial analysts to make more informed investment decisions.
  9. **Language Learning and Education**: Fast language models can provide instant feedback and adaptive language learning, making language education more effective and engaging.
  10. **Domain-Specific Knowledge Extraction**: Fast language models can quickly extract relevant information from vast amounts of text data, enabling domain experts to focus on high-level decision-making rather than manual information gathering.

The benefits of fast language models include:
- **Increased Efficiency**: Fast language models can process large amounts of text data quickly, reducing the time and effort required for tasks such as sentiment analysis, entity recognition, and text summarization.
- **Improved Accuracy**: Fast language models can analyze and learn from large datasets, leading to more accurate results and more informed decision-making.
- **Enhanced User Experience**: Fast language models can enable real-time interactions, personalized recommendations, and timely responses, improving the overall user experience.
- **Cost Savings**: Fast language models can automate many tasks, reducing the need for manual labor and minimizing costs associated with data processing and analysis.

In summary, fast language models have the potential to transform various industries and applications by providing fast, accurate, and efficient language processing capabilities.

## Chat Completion Request

- **Description**: A document that can be referenced by the model while generating responses.
- **Properties**:
  - **id**: Optional unique identifier that can be used for citations in responses.
  - **source**: Document containing the text content.

## Chat Completion Response

- **Description**: A chat completion message generated by the model.
- **Properties**:
  - **annotations**: A list of annotations providing citations and references for the content in the message.
  - **content**: The contents of the message.
  - **executed_tools**: Information about the tools that were executed during the chat completion for compound AI systems.
  - **function_call**: Controls which (if any) function is called by the model.
  - **reasoning**: The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
  - **role**: The role of the messages author, in this case `assistant`.
  - **tool_calls**: The tool calls generated by the model, such as function calls.

## Chat Completion Role

- **Description**: The role of the author of a message.
- **Values**:
  - `system`
  - `user`
  - `assistant`
  - `tool`
  - `developer`

## Chat Completion Stream

- **Description**: A chat completion delta generated by streamed model responses.
- **Properties**:
  - **annotations**: A list of annotations providing citations and references for the content in the message.
  - **content**: The contents of the chunk message.
  - **executed_tools**: Information about the tools that were executed during the chunk.
  - **reasoning**: The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
  - **role**: The role of the author of this message.
  - **tool_calls**: The tools that were available to the model.

## Chat Completion Token Logprob

- **Description**: A list of tokens with log probability information.
- **Properties**:
  - **bytes**: A list of integers representing the UTF-8 bytes representation of the token.
  - **logprob**: The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely.

## Chat Completion Tool

- **Description**: Describes a tool that the model may generate JSON inputs for.
- **Properties**:
  - **name**: The name of the function to be called.
  - **parameters**: A JSON schema describing the function's input parameters.

## Chat Completion Response Message

- **Description**: A message input to the model with a role indicating instruction following hierarchy.
- **Properties**:
  - **content**: A list of one or many input content items.
  - **role**: The role of the message input.
  - **status**: The status of the message.
  - **type**: The type of the message input.

## Chat Completion Response FileCitation

- **Description**: A citation to a file.
- **Properties**:
  - **file_id**: The ID of the file.
  - **index**: The index of the citation in the text.
  - **type**: The type of the annotation. Always `file_citation`.
  - **url**: The URL of the file.

## Chat Completion Response TextCitation

- **Description**: A citation for a web resource.
- **Properties**:
  - **end_index**: The character index in the URL citation in the message.
  - **start_index**: The character index in the URL citation in the message.
  - **title**: The title of the web resource.
  - **type**: The type of the annotation. Always `url_citation`.
  - **url**: The URL of the web resource.

## Chat Completion Usage Breakdown

- **Description**: Usage statistics for compound AI completion requests.
- **Properties**:
  - **models**: List of models used in the request and their individual usage statistics.
  - **type**: The type of the response format being defined. Always `json_object`.

## Chat Completion Response

- **Description**: Represents a response returned by model, based on the provided input.
- **Properties**:
  - **background**: Whether the response was generated in the background.
  - **created_at**: The Unix timestamp (in seconds) of when the response was created.
  - **error**: An error object if the response failed.
  - **id**: A unique identifier for the response.
  - **incomplete_details**: Details about why the response is incomplete.
  - **instructions**: The system instructions used for the response.
  - **max_output_tokens**: An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
  - **metadata**: Additional key-value pairs for storing additional information.
  - **model**: The model used for the response.
  - **object**: The object type, which is always `chat.completion`.
  - **output**: An array of content items generated by the model.
  - **parallel_tool_calls**: Whether the model can run tool calls in parallel.
  - **previous_response_id**: Not supported. Always null.
  - **reasoning**: Configuration options for [models that support reasoning](https://console.groq.com/docs/reasoning).
  - **response_format**: An object specifying the format that the model must output.
  - **stream**: Enable streaming mode to receive response data as server-sent events.
  - **temperature**: Controls randomness in the response generation.
  - **tool_choice**: Controls which (if any) tool is called by the model.
  - **tools**: List of tools available to the model.
  - **top_logprobs**: The number of top log probabilities returned.
  - **top_p**: The nucleus sampling parameter used.
  - **truncation**: The truncation strategy used.
  - **usage**: Usage information for the request.
  - **user**: Optional identifier for tracking end-user requests.

## Chat Completion Stream Response

- **Description**: Represents a streamed chunk of a chat completion response returned by model, based on the provided input.
- **Properties**:
  - **annotations**: A list of annotations providing citations and references for the content in the message.
  - **content**: The contents of the chunk message.
  - **executed_tools**: Information about the tools that were executed during the chunk.
  - **reasoning**: The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
  - **role**: The role of the author of this message.
  - **tool_calls**: The tool calls generated by the model.

## Chat Completion Response Message

- **Description**: A message input to the model with explicit type field.
- **Properties**:
  - **content**: A list of one or many input content items.
  - **role**: The role of the message input.
  - **status**: The status of item. Populated when items are returned via API.
  - **type**: The type of the message input.

## Chat Completion Response TextCitation

- **Description**: A text input to the model.
- **Properties**:
  - **text**: The text input to the model.
  - **type**: The type of the input item. Always `input_text`.

## Chat Completion Response FileCitation

- **Description**: A citation to a file.
- **Properties**:
  - **file_id**: The ID of the file.
  - **index**: The index of the citation in the text.
  - **type**: The type of the annotation. Always `file_citation`.
  - **url**: The URL of the file.

## Chat Completion Response TextContent

- **Description**: A text output from the model.
- **Properties**:
  - **annotations**: The annotations of the text output.
  - **logprobs**: Log probability information for the output.
  - **text**: The text output from the model.
  - **type**: The type of the output text. Always `output_text`.

## Chat Completion Response FunctionCall

- **Description**: A function call generated by the model.
- **Properties**:
  - **arguments**: A JSON string of the arguments to pass to the function.
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call.
  - **name**: The name of the function to call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Response FunctionCallOutput

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item. Populated when items are returned via API.

## Chat Completion Response EasyInputMessage

- **Description**: A message input to the model with explicit type field.
- **Properties**:
  - **content**: A list of one or many input content items.
  - **role**: The role of the message input.
  - **status**: The status of item. Populated when items are returned via API.
  - **type**: The type of the message input. Always `message`.

## Chat Completion Response FileCitation

- **Description**: A citation to a file.
- **Properties**:
  - **end_index**: The character index in the URL citation in the message.
  - **start_index**: The character index in the URL citation in the message.
  - **title**: The title of the file.
  - **type**: The type of the annotation. Always `url_citation`.
  - **url**: The URL of the file.

## Chat Completion Response Usage

- **Description**: Usage statistics for the response request.
- **Properties**:
  - **input_tokens**: Number of tokens in the input.
  - **input_tokens_details**: Breakdown of input tokens.
  - **output_tokens**: Number of tokens in the generated output.
  - **output_tokens_details**: Breakdown of output tokens.
  - **total_tokens**: Total number of tokens used in the request (input + output).

## Text Response Format JsonSchema

- **Description**: JSON Schema response format. Used to generate structured JSON responses.
- **Properties**:
  - **description**: A description of what the response format is for, used by the model to determine how to respond in the format.
  - **name**: The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
  - **schema**: The schema for the response format, described as a JSON Schema object.
  - **strict**: Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the `schema` field. Only a subset of JSON Schema is supported when `strict` is `true`.

## Transcription Segment

- **Description**: A citation for a web resource.
- **Properties**:
  - **audio_text**: Transcribed text for the entire chunk.
  - **avg_logprob**: Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.
  - **chunk_end**: End chunk timestamp.
  - **chunk_start**: Start chunk timestamp.
  - **compression_ratio**: Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.
  - **end**: End time of the segment in seconds.
  - **id**: Unique identifier of the segment.
  - **no_speech_prob**: Probability of no speech in the segment. If the value is higher than 1.0 and the `avg_logprob` is below -1, consider this segment silent.
  - **seek**: Seek offset of the segment.
  - **start**: Start time of the segment in seconds.
  - **temperature**: Temperature parameter used for generating the segment.
  - **text**: Text content of the segment.
  - **token_scores**: Token-level scores.
  - **tokens**: Array of token IDs for the text content.

## XGroq Metadata

- **Description**: Groq-specific metadata for streaming responses.
- **Properties**:
  - **debug**: An array of DebugData objects.
  - **error**: An error string indicating why a stream was stopped early.
  - **id**: A groq request ID which can be used to refer to a specific request to groq support.
  - **seed**: The seed used for the request.
  - **usage**: Additional Groq-specific usage metrics (hardware cache statistics).

## XGroq NonStreaming Metadata

- **Description**: Groq-specific metadata for non-streaming chat completion responses.
- **Properties**:
  - **debug**: An array of DebugData objects.
  - **id**: A groq request ID which can be used to refer to a specific request to groq support.
  - **seed**: The seed used for the request.
  - **usage**: Additional Groq-specific usage metrics (hardware cache statistics).

## Groq Cloud API Specification

- **Contact**: Support@groq.com
- **Description**: Specification of the Groq cloud API
- **Terms of Service**: https://groq.com/terms-of-use/
- **Title**: GroqCloud API
- **Version**: 2.1

## Groq API Endpoints

- **/openai/v1/audio/speech**
  - **Post**: Generates audio from the input text.
  - **Description**: OK
  - **Tags**: Audio

- **/openai/v1/audio/transcriptions**
  - **Post**: Transcribes audio into the input language.
  - **Description**: OK
  - **Tags**: Audio

- **/openai/v1/audio/translations**
  - **Post**: Translates audio into English.
  - **Description**: OK
  - **Tags**: Audio

- **/openai/v1/batches**
  - **Get**: List your organization's batches.
  - **Summary**: List your organization's batches.
  - **Tags**: Batch
  - **X-groq-metadata**: Examples: Default

- **/openai/v1/batches/{batch_id}**
  - **Get**: Retrieves a batch.
  - **Summary**: Retrieves a batch.
  - **Tags**: Batch
  - **X-groq-metadata**: Examples: Default

- **/openai/v1/batches/{batch_id}/cancel**
  - **Post**: Cancels a batch.
  - **Summary**: Cancels a batch.
  - **Tags**: Batch
  - **X-groq-metadata**: Examples: Default

- **/openai/v1/chat/completions**
  - **Post**: Creates a model response for the given chat conversation.
  - **Description**: OK
  - **Tags**: Chat
  - **X-groq-metadata**: Examples: Default

- **/openai/v1/embeddings**
  - **Post**: Creates an embedding vector representing the input text.
  - **Description**: OK
  - **Tags**: Embeddings

- **/openai/v1/files**
  - **Get**: Returns a list of files.
  - **Summary**: Returns a list of files.
  - **Tags**: Files
  - **X-groq-metadata**: Examples: Default

- **/openai/v1/files/{file_id}**
  - **Delete**: Delete a file.
  - **Summary**: Delete a file.
  - **Tags**: Files
  - **X-groq-metadata**: Examples: Default

- **/openai/v1/files/{file_id}/content**
  - **Get**: Returns the contents of the specified file.
  - **Summary**: Returns the contents of the specified file.
  - **Tags**: Files

- **/openai/v1/models**
  - **Get**: Get all available models.
  - **Summary**: Get all available models.
  - **Tags**: Models
  - **X-groq-metadata**: Examples: Default

- **/openai/v1/reranking**
  - **Post**: Given a query and a list of documents, returns the documents ranked by their relevance to the query.
  - **Description**: Reranks documents based on their relevance to a query.
  - **Tags**: Reranking
  - **X-groq-metadata**: Examples: Basic Reranking, Reranking with Custom Instruction

- **/openai/v1/responses**
  - **Post**: The input prompt and parameters.
  - **Description**: OK
  - **Tags**: Responses
  - **X-groq-metadata**: Examples: Default

- **/v1/fine_tunings**
  - **Get**: List all previously created fine tunings.
  - **Summary**: List all previously created fine tunings.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

- **/v1/fine_tunings/{id}**
  - **Delete**: Deletes an existing fine tuning by id.
  - **Summary**: Deletes an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses/{id}**
  - **Get**: Retrieves an existing fine tuning by id.
  - **Summary**: Retrieves an existing fine tuning by id.
  - **Tags**: Fine Tuning
  - **X-groq-metadata**: Examples: Default

## Groq API Endpoints

- **/openai/v1/responses

---

# Source: https://docs.groq.com/docs/speech-text

# Overview - GroqDocs

## Welcome

Fast LLM inference, OpenAI-compatible. Simple to integrate, easy to scale. Start building in minutes.

## External API Compatibility

- **OpenAI base URL:** [https://api.groq.com/openai/v1](https://api.groq.com/openai/v1)
- **Gemma2-9b-it:** [https://console.groq.com/docs/models/gemma2-9b-it](https://console.groq.com/docs/models/gemma2-9b-it)
- **Llama3-8b-8192:** [https://console.groq.com/docs/models/llama3-8b-8192](https://console.groq.com/docs/models/llama3-8b-8192)
- **Llama3-70b-8192:** [https://console.groq.com/docs/models/llama3-70b-8192](https://console.groq.com/docs/models/llama3-70b-8192)
- **Whisper-large-v3-turbo:** [https://console.groq.com/docs/models/whisper-large-v3-turbo](https://console.groq.com/docs/models/whisper-large-v3-turbo)
- **Whisper-large-v3:** [https://console.groq.com/docs/models/whisper-large-v3](https://console.groq.com/docs/models/whisper-large-v3)
- **Llama Guard-3-8b:** [https://console.groq.com/docs/models/llama-guard-3-8b](https://console.groq.com/docs/models/llama-guard-3-8b)
- **Meta Llama/llama-4-maverick-17b-128e-instruct:** [https://console.groq.com/docs/models/meta-llama/llama-4-maverick-17b-128e-instruct](https://console.groq.com/docs/models/meta-llama/llama-4-maverick-17b-128e-instruct)
- **Meta Llama/llama-4-scout-17b-16e-instruct:** [https://console.groq.com/docs/models/meta-llama/llama-4-scout-17b-16e-instruct](https://console.groq.com/docs/models/meta-llama/llama-4-scout-17b-16e-instruct)
- **Meta Llama/llama-guard-4-12b:** [https://console.groq.com/docs/models/meta-llama/llama-guard-4-12b](https://console.groq.com/docs/models/meta-llama/llama-guard-4-12b)
- **Moonshot AI/Kimi-K2-Instruct:** [https://console.groq.com/docs/models/moonshotai/kimi-k2-instruct](https://console.groq.com/docs/models/moonshotai/kimi-k2-instruct)
- **OpenAI/gpt-oss-120b:** [https://console.groq.com/docs/models/openai/gpt-oss-120b](https://console.groq.com/docs/models/openai/gpt-oss-120b)
- **OpenAI/gpt-oss-20b:** [https://console.groq.com/docs/models/openai/gpt-oss-20b](https://console.groq.com/docs/models/openai/gpt-oss-20b)
- **Qwen/Qwen3-32b:** [https://console.groq.com/docs/models/qwen/qwen3-32b](https://console.groq.com/docs/models/qwen/qwen3-32b)

## Chat Completion

- **Description:** Fast language models have gained significant attention in recent years due to their ability to process and generate human-like text quickly and efficiently. The importance of fast language models can be understood from their potential applications and benefits:
  1. **Real-time Chatbots and Conversational Interfaces:** Fast language models enable the development of chatbots and conversational interfaces that can respond promptly to user queries, making them more engaging and useful.
  2. **Sentiment Analysis and Opinion Mining:** Fast language models can quickly analyze text data to identify sentiments, opinions, and emotions, allowing for improved customer service, market research, and opinion mining.
  3. **Language Translation and Localization:** Fast language models can quickly translate text between languages, facilitating global communication and enabling businesses to reach a broader audience.
  4. **Text Summarization and Generation:** Fast language models can summarize long documents or even generate new text on a given topic, improving information retrieval and processing efficiency.
  5. **Named Entity Recognition and Information Extraction:** Fast language models can rapidly recognize and extract specific entities, such as names, locations, and organizations, from unstructured text data.
  6. **Recommendation Systems:** Fast language models can analyze large amounts of text data to personalize product recommendations, improve customer experience, and increase sales.
  7. **Content Generation for Social Media:** Fast language models can quickly generate engaging content for social media platforms, helping businesses maintain a consistent online presence and increasing their online visibility.
  8. **Sentiment Analysis for Stock Market Analysis:** Fast language models can quickly analyze social media posts, news articles, and other text data to identify sentiment trends, enabling financial analysts to make more informed investment decisions.
  9. **Language Learning and Education:** Fast language models can provide instant feedback and adaptive language learning, making language education more effective and engaging.
  10. **Domain-Specific Knowledge Extraction:** Fast language models can quickly extract relevant information from vast amounts of text data, enabling domain experts to focus on high-level decision-making rather than manual information gathering.

- **Benefits:** 
  - **Increased Efficiency:** Fast language models can process large amounts of text data quickly, reducing the time and effort required for tasks such as sentiment analysis, entity recognition, and text summarization.
  - **Improved Accuracy:** Fast language models can analyze and learn from large datasets, leading to more accurate results and more informed decision-making.
  - **Enhanced User Experience:** Fast language models can enable real-time interactions, personalized recommendations, and timely responses, improving the overall user experience.
  - **Cost Savings:** Fast language models can automate many tasks, reducing the need for manual labor and minimizing costs associated with data processing and analysis.

- **In summary:** Fast language models have the potential to transform various industries and applications by providing fast, accurate, and efficient language processing capabilities.

## Chat Completion Request

- **Description:** A document that can be referenced by the model while generating responses.
- **Properties:**
  - **Document Citation:** An optional citation referencing a specific document that was provided in the request.
  - **Source:** The source of the document. Only text and JSON sources are currently supported.
- **Type:** `document_citation` or `function_citation`.

## Chat Completion Response

- **Description:** A chat completion message generated by the model.
- **Properties:**
  - **Annotation:** A list of annotations providing citations and references for the content in the message.
  - **Content:** The contents of the message.
  - **Executed Tools:** A list of tools that were executed during the chat completion for compound AI systems.
  - **Function Call:** Controls which (if any) tool is called by the model.
  - **Reasoning:** The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
  - **Role:** The role of the messages author, in this case `assistant`.
  - **Tool Calls:** A list of tool calls generated by the model, such as function calls.

## Chat Completion Role

- **Description:** The role of the author of a message.
- **Options:**
  - `system`
  - `user`
  - `assistant`
  - `tool`
  - `function`

## Chat Completion Stream

- **Description:** A chat completion delta generated by streamed model responses.
- **Properties:**
  - **Annotation:** A list of annotations providing citations and references for the content in the message.
  - **Content:** The contents of the chunk message.
  - **Executed Tools:** Log probability information for the choice.
  - **Reasoning:** The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
  - **Role:** The role of the author of this message.
  - **Tool Calls:** The tool calls that were available to the model.
  - **Top Log Probabilities:** The number of most likely tokens at each token position, each with an associated log probability.

## Chat Completion Usage Breakdown

- **Description:** Usage statistics for compound AI completion requests.
- **Properties:**
  - **Models:** List of models used in the request and their individual usage statistics.
  - **Type:** `list`.

## Chat Completion Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** The arguments to call the function with, as generated by the model in JSON format.
  - **Name:** The name of the function to call.
  - **Type:** `function`.

## Chat Completion Message Tool Call

- **Description:** Controls which (if any) tool is called by the model.
- **Properties:**
  - **Function:** The function that the model called.
  - **Name:** The name of the function to call.
  - **Type:** `function`.

## Chat Completion Message Tool Call Chunk

- **Description:** Controls which (if any) tool is called by the model.
- **Properties:**
  - **Function:** The function that the model called.
  - **Name:** The name of the function to call.
  - **Type:** `function`.

## Chat Completion Message Tool Calls

- **Description:** The tool calls generated by the model, such as function calls.

## Chat Completion Message Tool Choice Option

- **Description:** Controls which (if any) tool is called by the model.
- **Properties:**
  - **Function:** The function that the model called.
  - **Name:** The name of the function to call.
  - **Type:** `function`.

## Chat Completion Response Message

- **Description:** A message input to the model with a role indicating instruction following hierarchy.
- **Properties:**
  - **Content:** Text input to the model.
  - **Role:** The role of the message input.
  - **Status:** The status of the message.

## Chat Completion Response Output

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.
  - **Log Probabilities:** Log probability information for the output.
  - **Text:** The text output from the model.
  - **Type:** The type of the output text. Always `output_text`.

## Chat Completion Response Function Call

- **Description:** A function call generated by the model.
- **Properties:**
  - **Arguments:** A JSON string of the arguments to pass to the function.
  - **Call ID:** The unique ID of the function tool call generated by the model.
  - **ID:** The unique ID of the function tool call.
  - **Name:** The name of the function to call.
  - **Status:** The status of the function call.

## Chat Completion Response Message

- **Description:** An output message from the model.
- **Properties:**
  - **Content:** The content of the output message.
  - **ID:** The unique ID of the output message.
  - **Role:** The role of the output message.
  - **Status:** The status of the message.

## Chat Completion Response Reasoning

- **Description:** A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).
- **Properties:**
  - **ID:** The unique ID of the reasoning output.
  - **Summary:** Summary items (currently empty).
  - **Type:** The type of the reasoning output. Always `reasoning`.

## Chat Completion Response Text

- **Description:** A text output from the model.
- **Properties:**
  - **Annotations:** The annotations of the text output.

---

# Source: https://docs.groq.com/docs/text-chat#streaming-a-chat-completion

# Overview - GroqDocs

## Welcome

Fast language models have gained significant attention in recent years due to their ability to process and generate human-like text quickly and efficiently. The importance of fast language models can be understood from their potential applications and benefits:

1. **Real-time Chatbots and Conversational Interfaces**: Fast language models enable the development of chatbots and conversational interfaces that can respond promptly to user queries, making them more engaging and useful.
2. **Sentiment Analysis and Opinion Mining**: Fast language models can quickly analyze text data to identify sentiments, opinions, and emotions, allowing for improved customer service, market research, and opinion mining.
3. **Language Translation and Localization**: Fast language models can quickly translate text between languages, facilitating global communication and enabling businesses to reach a broader audience.
4. **Text Summarization and Generation**: Fast language models can summarize long documents or even generate new text on a given topic, improving information retrieval and processing efficiency.
5. **Named Entity Recognition and Information Extraction**: Fast language models can rapidly recognize and extract specific entities, such as names, locations, and organizations, from unstructured text data.
6. **Recommendation Systems**: Fast language models can analyze large amounts of text data to personalize product recommendations, improve customer experience, and increase sales.
7. **Content Generation for Social Media**: Fast language models can quickly generate engaging content for social media platforms, helping businesses maintain a consistent online presence and increasing their online visibility.
8. **Sentiment Analysis for Stock Market Analysis**: Fast language models can quickly analyze social media posts, news articles, and other text data to identify sentiment trends, enabling financial analysts to make more informed investment decisions.
9. **Language Learning and Education**: Fast language models can provide instant feedback and adaptive language learning, making language education more effective and engaging.
10. **Domain-Specific Knowledge Extraction**: Fast language models can quickly extract relevant information from vast amounts of text data, enabling domain experts to focus on high-level decision-making rather than manual information gathering.

The benefits of fast language models include:

- **Increased Efficiency**: Fast language models can process large amounts of text data quickly, reducing the time and effort required for tasks such as sentiment analysis, entity recognition, and text summarization.
- **Improved Accuracy**: Fast language models can analyze and learn from large datasets, leading to more accurate results and more informed decision-making.
- **Enhanced User Experience**: Fast language models can enable real-time interactions, personalized recommendations, and timely responses, improving the overall user experience.
- **Cost Savings**: Fast language models can automate many tasks, reducing the need for manual labor and minimizing costs associated with data processing and analysis.

In summary, fast language models have the potential to transform various industries and applications by providing fast, accurate, and efficient language processing capabilities.

## External API Compatibility

- **gemma2-9b-it**
- **llama3-8b-8192**
- **llama3-70b-8192**
- **whisper-large-v3-turbo**
- **whisper-large-v3**
- **llama-guard-3-8b**
- **meta-llama/llama-4-maverick-17b-128e-instruct**
- **meta-llama/llama-4-scout-17b-16e-instruct**
- **meta-llama/llama-guard-4-12b**
- **moonshotai/kimi-k2-instruct**
- **openai/gpt-oss-120b**
- **openai/gpt-oss-20b**
- **qwen/qwen3-32b**

## Chat Completion

- **Fast language models have gained significant attention in recent years due to their ability to process and generate human-like text quickly and efficiently. The importance of fast language models can be understood from their potential applications and benefits:**
  1. **Real-time Chatbots and Conversational Interfaces**: Fast language models enable the development of chatbots and conversational interfaces that can respond promptly to user queries, making them more engaging and useful.
  2. **Sentiment Analysis and Opinion Mining**: Fast language models can quickly analyze text data to identify sentiments, opinions, and emotions, allowing for improved customer service, market research, and opinion mining.
  3. **Language Translation and Localization**: Fast language models can quickly translate text between languages, facilitating global communication and enabling businesses to reach a broader audience.
  4. **Text Summarization and Generation**: Fast language models can summarize long documents or even generate new text on a given topic, improving information retrieval and processing efficiency.
  5. **Named Entity Recognition and Information Extraction**: Fast language models can rapidly recognize and extract specific entities, such as names, locations, and organizations, from unstructured text data.
  6. **Recommendation Systems**: Fast language models can analyze large amounts of text data to personalize product recommendations, improve customer experience, and increase sales.
  7. **Content Generation for Social Media**: Fast language models can quickly generate engaging content for social media platforms, helping businesses maintain a consistent online presence and increasing their online visibility.
  8. **Sentiment Analysis for Stock Market Analysis**: Fast language models can quickly analyze social media posts, news articles, and other text data to identify sentiment trends, enabling financial analysts to make more informed investment decisions.
  9. **Language Learning and Education**: Fast language models can provide instant feedback and adaptive language learning, making language education more effective and engaging.
  10. **Domain-Specific Knowledge Extraction**: Fast language models can quickly extract relevant information from vast amounts of text data, enabling domain experts to focus on high-level decision-making rather than manual information gathering.

The benefits of fast language models include:

- **Increased Efficiency**: Fast language models can process large amounts of text data quickly, reducing the time and effort required for tasks such as sentiment analysis, entity recognition, and text summarization.
- **Improved Accuracy**: Fast language models can analyze and learn from large datasets, leading to more accurate results and more informed decision-making.
- **Enhanced User Experience**: Fast language models can enable real-time interactions, personalized recommendations, and timely responses, improving the overall user experience.
- **Cost Savings**: Fast language models can automate many tasks, reducing the need for manual labor and minimizing costs associated with data processing and analysis.

In summary, fast language models have the potential to transform various industries and applications by providing fast, accurate, and efficient language processing capabilities.

## API Reference

- **Chat Completion**
  - **Description**: A chat completion message generated by the model.
  - **Properties**:
    - **annotations**: A list of annotations providing citations and references for the content in the message.
    - **content**: The contents of the message.
    - **executed_tools**: A list of tools that were executed during the chat completion for compound AI systems.
    - **function_call**: Controls which (if any) function is called by the model.
    - **reasoning**: The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
    - **role**: The role of the author of this message.
    - **tool_calls**: A list of tool calls generated by the model, such as function calls.
  - **Type**: Array of content items generated by the model.

- **Response Annotation**
  - **Description**: A citation referencing a specific document that was provided in the request.
  - **Properties**:
    - **document_id**: The ID of the document being cited, corresponding to a document provided in the request.
    - **end_index**: The character index in the message content where this citation ends.
    - **start_index**: The character index in the message content where this citation begins.
  - **Type**: Object.

- **Embedding**
  - **Description**: Represents an embedding vector returned by embedding endpoint.
  - **Properties**:
    - **embedding**: A list of floats representing the embedding vector. The length of vector depends on the model as listed in the [embedding guide](https://console.groq.com/docs/guides/embeddings).
    - **index**: The index of the embedding in the list of embeddings.
    - **object**: The object type, which is always `embedding`.
  - **Type**: Object.

- **Error**
  - **Description**: An error object if the response failed.
  - **Properties**:
    - **code**: The error code.
    - **debug**: An error string indicating why a stream was stopped early.
    - **message**: A human-readable error message.
    - **param**: Optional.
    - **schema_code**: Optional.
    - **schema_kind**: Optional.
    - **schema_path**: Optional.
    - **schema_path_segments**: Optional.
  - **Type**: Object.

- **ErrorResponse**
  - **Description**: Returns an error response.
  - **Properties**:
    - **error**: An error object.
  - **Type**: Object.

- **File**
  - **Description**: The `File` object represents a document that has been uploaded.
  - **Properties**:
    - **bytes**: The size of the file, in bytes.
    - **created_at**: The Unix timestamp (in seconds) for when the file was created.
    - **filename**: The name of the file.
    - **id**: The file identifier, which can be referenced in the API endpoints.
    - **object**: The object type, which is always `file`.
    - **purpose**: The intended purpose of the file. Supported values are `batch` and `batch_output`.
  - **Type**: Object.

- **FunctionCitation**
  - **Description**: A citation referencing the result of a function or tool call.
  - **Properties**:
    - **end_index**: The character index in the message content where this citation ends.
    - **start_index**: The character index in the message content where this citation begins.
    - **tool_call_id**: The ID of the tool call being cited, corresponding to a tool call made during the conversation.
  - **Type**: Object.

- **FunctionObject**
  - **Description**: Describes the function's purpose. The model uses this to determine when to invoke the function.
  - **Properties**:
    - **description**: A description of what the function does.
    - **name**: The name of the function to be called.
    - **parameters**: A JSON schema describing the function's input parameters.
    - **strict**: Whether to enable strict schema adherence when generating the output.
  - **Type**: Object.

- **FunctionParameters**
  - **Description**: Function parameters defined as a JSON Schema object.
  - **Type**: Object.

- **ListBatchesResponse**
  - **Description**: A list of batches.
  - **Properties**:
    - **data**: A list of batches.
  - **Type**: Array.

- **ListFilesResponse**
  - **Description**: A list of files.
  - **Properties**:
    - **data**: A list of files.
  - **Type**: Array.

- **ListFineTuningsResponse**
  - **Description**: A list of fine tunings.
  - **Properties**:
    - **data**: A list of fine tunings.
  - **Type**: Array.

- **ListModelsResponse**
  - **Description**: A list of models.
  - **Properties**:
    - **data**: A list of models.
  - **Type**: Array.

- **Model**
  - **Description**: Describes an OpenAI model offering that can be used with the API.
  - **Properties**:
    - **created**: The Unix timestamp (in seconds) when the model was created.
    - **id**: The model identifier, which can be referenced in the API endpoints.
    - **object**: The object type, which is always `model`.
    - **owned_by**: The organization that owns the model.
  - **Type**: Object.

- **ReadFineTuningResponse**
  - **Description**: Returns a fine tune object.
  - **Properties**:
    - **data**: A fine tune object.
  - **Type**: Object.

- **ReadTranslationResponse**
  - **Description**: Returns a translation object.
  - **Properties**:
    - **text**: The translated text.
  - **Type**: Object.

- **ResponseAnnotation**
  - **Description**: A citation referencing a file.
  - **Properties**:
    - **end_index**: The character index of the last character of the URL citation in the message.
    - **start_index**: The character index of the first character of the URL citation in the message.
    - **title**: The title of the URL resource.
    - **type**: The type of the annotation. Always `url_citation`.
  - **Type**: Object.

- **ResponseEasyInputMessage**
  - **Description**: A message input to the model with a role indicating instruction following hierarchy.
  - **Properties**:
    - **content**: A list of one or many input content items.
    - **role**: The role of the message input. One of `user`, `assistant`, `system`, or `developer`.
    - **status**: The status of the item. Populated when items are returned via API.
  - **Type**: Object.

- **ResponseFileCitation**
  - **Description**: A citation to a file.
  - **Properties**:
    - **end_index**: The character index of the last character of the URL citation in the message.
    - **start_index**: The character index of the first character of the URL citation in the message.
    - **title**: The title of the file resource.
    - **type**: The type of the annotation. Always `file_citation`.
  - **Type**: Object.

- **ResponseFormatConfiguration**
  - **Description**: An object specifying the format that the model must output.
  - **Properties**:
    - **description**: A description of what the response format is for, used by the model to determine how to respond in the format.
    - **name**: The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
    - **schema**: A JSON Schema object describing the response format.
    - **strict**: Whether to enable strict schema adherence when generating the output.
  - **Type**: Object.

- **ResponseFormatJsonSchema**
  - **Description**: JSON Schema response format.
  - **Properties**:
    - **type**: The type of response format being defined. Always `json_schema`.
  - **Type**: Object.

- **ResponseFormatText**
  - **Description**: Default response format.
  - **Properties**:
    - **type**: The type of response format being defined. Always `text`.
  - **Type**: Object.

- **ResponseFunctionCall**
  - **Description**: A function call generated by the model.
  - **Properties**:
    - **arguments**: A JSON string of the arguments to pass to the function.
    - **call_id**: The unique ID of the function tool call generated by the model.
    - **id**: The unique ID of the function tool call.
    - **name**: The name of the function to call.
    - **status**: The status of the function call.
  - **Type**: Object.

- **ResponseOutputContent**
  - **Description**: A text output from the model.
  - **Properties**:
    - **annotations**: The annotations of the text output.
    - **logprobs**: Log probability information for the output.
    - **text**: The text output from the model.
    - **type**: The type of the output text. Always `output_text`.
  - **Type**: Object.

- **ResponseTool**
  - **Description**: A function call generated by the model.
  - **Properties**:
    - **arguments**: A JSON string of the arguments to pass to the function.
    - **call_id**: The unique ID of the function tool call generated by the model.
    - **id**: The unique ID of the function tool call.
    - **name**: The name of the function to call.
    - **status**: The status of the function call.
  - **Type**: Object.

- **ResponseToolChoiceOption**
  - **Description**: Controls which (if any) tool is called by the model.
  - **Properties**:
    - **function**: Controls which (if any) tool is called by the model.
    - **type**: The type of the tool. Currently, only `function` is supported.
  - **Type**: Object.

- **ResponseUrlCitation**
  - **Description**: A citation for a web resource.
  - **Properties**:
    - **end_index**: The character index of the URL citation in the message.
    - **start_index**: The character index of the first character of the URL citation in the message.
    - **title**: The title of the web resource.
    - **type**: The type of the annotation. Always `url_citation`.
  - **Type**: Object.

- **ResponseUsage**
  - **Description**: Usage statistics for the response request.
  - **Properties**:
    - **input_tokens**: Number of tokens in the input.
    - **input_tokens_details**: Breakdown of input tokens.
    - **output_tokens**: Number of tokens in the generated output.
    - **output_tokens_details**: Breakdown of output tokens.
    - **total_tokens**: Total number of tokens used in the request (input + output).
  - **Type**: Object.

- **TextResponseFormatJsonSchema**
  - **Description**: JSON Schema response format.
  - **Properties**:
    - **description**: A description of what the response format is for, used by the model to determine how to respond in the format.
    - **name**: The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
    - **schema**: A JSON Schema object describing the response format.
    - **strict**: Whether to enable strict schema adherence when generating the output.
  - **Type**: Object.

- **TranscriptionSegment**
  - **Description**: A segment of the audio.
  - **Properties**:
    - **audio_text**: Transcribed text for the entire chunk.
    - **avg_logprob**: Average logprob of the segment. If the value is lower than -1, consider the logprobs failed.
    - **chunk_end**: End chunk timestamp.
    - **chunk_start**: Start chunk timestamp.
    - **compression_ratio**: Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed.
    - **end**: End time of the segment in seconds.
    - **id**: Unique identifier of the segment.
    - **no_speech_prob**: Probability of no speech in the segment. If the value is higher than 1.0 and the `avg_logprob` is below -1, consider this segment silent.
    - **seek**: Seek offset of the segment.
    - **start**: Start time of the segment in seconds.
    - **temperature**: Temperature parameter used for generating the segment.
    - **text**: Text content of the segment.
    - **token_scores**: Token-level scores.
    - **tokens**: Array of token IDs for the text content.
  - **Type**: Object.

- **XGroq**
  - **Description**: Groq-specific metadata for streaming responses.
  - **Properties**:
    - **debug**: An error string indicating why a stream was stopped early.
    - **id**: A groq request ID which can be used to refer to a specific request to groq support.
    - **seed**: The seed used for the request. Sent in the final chunk.
    - **usage**: Additional Groq-specific usage metrics (hardware cache statistics).
  - **Type**: Object.

- **XGroqNonStreaming**
  - **Description**: Groq-specific metadata for non-streaming chat completion responses.
  - **Properties**:
    - **debug**: An error string indicating why a stream was stopped early.
    - **id**: A groq request ID which can be used to refer to a specific request to groq support.
    - **seed**: The seed used for the request. See the seed property on CreateChatCompletionRequest for more details.
    - **usage**: Additional Groq-specific usage metrics (hardware cache statistics).
  - **Type**: Object.

## Chat Completion

- **Description**: A chat completion message generated by the model.
- **Properties**:
  - **annotations**: A list of annotations providing citations and references for the content in the message.
  - **content**: The contents of the message.
  - **executed_tools**: A list of tools that were executed during the chat completion for compound AI systems.
  - **function_call**: Controls which (if any) function is called by the model.
  - **reasoning**: The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
  - **role**: The role of the author of this message.
  - **tool_calls**: A list of tool calls generated by the model, such as function calls.
- **Type**: Array of content items generated by the model.

## Response

- **Description**: A message input to the model with explicit type field.
- **Properties**:
  - **content**: A list of one or many input content items.
  - **role**: The role of the message input. One of `user`, `assistant`, `system`, or `developer`.
  - **status**: The status of item. Populated when items are returned via API.
- **Type**: Object.

## Fine Tuning

- **Description**: A fine tuning for the already uploaded files.
- **Properties**:
  - **input_file_id**: The ID of an uploaded file that contains requests for the new batch.
  - **model**: The name of the fine tuned model.
  - **type**: The type of fine tuning format such as `lora`.
- **Type**: Object.

## Model

- **Description**: Describes an OpenAI model offering that can be used with the API.
- **Properties**:
  - **created**: The Unix timestamp (in seconds) when the model was created.
  - **id**: The model identifier, which can be referenced in the API endpoints.
  - **object**: The object type, which is always `model`.
  - **owned_by**: The organization that owns the model.
- **Type**: Object.

## Embedding

- **Description**: Represents an embedding vector representing the input text.
- **Properties**:
  - **embedding**: A list of floats representing the embedding vector. The length of vector depends on the model as listed in the [embedding guide](https://console.groq.com/docs/guides/embeddings).
  - **index**: The index of the embedding in the list of embeddings.
- **Type**: Object.

## File

- **Description**: The `File` object represents a document that has been uploaded.
- **Properties**:
  - **bytes**: The size of the file, in bytes.
  - **created_at**: The Unix timestamp (in seconds) for when the file was created.
  - **filename**: The name of the file.
  - **id**: The file identifier, which can be referenced in the API endpoints.
  - **object**: The object type, which is always `file`.
  - **purpose**: The intended purpose of the file. Supported values are `batch` and `batch_output`.
- **Type**: Object.

## Batch

- **Description**: List your organization's batches.
- **Properties**:
  - **data**: A list of batches.
- **Type**: Array.

## Batch

- **Description**: Creates and executes a batch from an uploaded file of requests.
- **Properties**:
  - **input_file_id**: The ID of an uploaded file that contains requests for the new batch.
  - **endpoint**: The endpoint to be used for all requests in the batch.
  - **completion_window**: The time frame within which the batch should be processed.
- **Type**: Object.

## Batch

- **Description**: Cancels a batch.
- **Properties**:
  - **input_file_id**: The ID of the batch to cancel.
- **Type**: Object.

## Batch

- **Description**: Returns a list of batches.
- **Properties**:
  - **object**: `list`.
  - **data**: `data`.
- **Type**: Array.

## Batch

- **Description**: Returns a batch object.
- **Properties**:
  - **id**: `batch_01jh6xa7reempvjyh6n3yst2zw`.
  - **object**: `batch`.
  - **endpoint**: `/v1/chat/completions`.
  - **errors**: `null`.
  - **input_file_id**: `file_01jh6x76wtemjr74t1fh0faj5t`.
  - **completion_window**: `24h`.
  - **status**: `validating`.
  - **output_file_id**: `null`.
  - **error_file_id**: `null`.
  - **finalizing_at**: `null`.
  - **failed_at**: `null`.
  - **expired_at**: `null`.
  - **cancelled_at**: `null`.
  - **request_counts**: `{ total: 0, completed: 0, failed: 0 }`.
  - **metadata**: `null`.
  - **created_at**: `1736472600`.
  - **expires_at**: `1736559000`.
  - **cancelling_at**: `null`.
  - **completed_at**: `null`.
  - **in_progress_at**: `null`.
- **Type**: Object.

## Batch

- **Description**: Returns an audio transcription object.
- **Properties**:
  - **text**: `Your transcribed text appears here...`.
- **Type**: Object.

## Batch

- **Description**: Returns an audio translation object.
- **Properties**:
  - **text**: `Your translated text appears here...`.
- **Type**: Object.

## Batch

- **Description**: Returns a batch object.
- **Properties**:
  - **id**: `batch_01jh6xa7reempvjyh6n3yst2zw`.
  - **object**: `batch`.
  - **endpoint**: `/v1/chat/completions`.
  - **errors**: `null`.
  - **input_file_id**: `file_01jh6x76wtemjr74t1fh0faj5t`.
  - **completion_window**: `24h`.
  - **status**: `validating`.
  - **output_file_id**: `null`.
  - **error_file_id**: `null`.
  - **finalizing_at**: `null`.
  - **failed_at**: `null`.
  - **expired_at**: `null`.
  - **cancelled_at**: `null`.
  - **request_counts**: `{ total: 0, completed: 0, failed: 0 }`.
  - **metadata**: `null`.
  - **created_at**: `1736472600`.
  - **expires_at**: `1736559000`.
  - **cancelling_at**: `null`.
  - **completed_at**: `null`.
  - **in_progress_at**: `null`.
- **Type**: Object.

## Batch

- **Description**: Returns a batch object.
- **Properties**:
  - **id**: `batch_01jh6xa7reempvjyh6n3yst2zw`.
  - **object**: `batch`.
  - **endpoint**: `/v1/chat/completions`.
  - **errors**: `null`.
  - **input_file_id**: `file_01jh6x76wtemjr74t1fh0faj5t`.
  - **completion_window**: `24h`.
  - **status**: `validating`.
  - **output_file_id**: `null`.
  - **error_file_id**: `null`.
  - **finalizing_at**: `null`.
  - **failed_at**: `null`.
  - **expired_at**: `null`.
  - **cancelled_at**: `null`.
  - **request_counts**: `{ total: 0, completed: 0, failed: 0 }`.
  - **metadata**: `null`.
  - **created_at**: `1736472600`.
  - **expires_at**: `1736559000`.
  - **cancelling_at**: `null`.
  - **completed_at**: `null`.
  - **in_progress_at**: `null`.
- **Type**: Object.

## Batch

- **Description**: Returns a batch object.
- **Properties**:
  - **id**: `batch_01jh6xa7reempvjyh6n3yst2zw`.
  - **object**: `batch`.
  - **endpoint**: `/v1/chat/completions`.
  - **errors**: `null`.
  - **input_file_id**: `file_01jh6x76wtemjr74t1fh0faj5t`.
  - **completion_window**: `24h`.
  - **status**: `validating`.
  - **output_file_id**: `null`.
  - **error_file_id**: `null`.
  - **finalizing_at**: `null`.
  - **failed_at**: `null`.
  - **expired_at**: `null`.
  - **cancelled_at**: `null`.
  - **request_counts**: `{ total: 0, completed: 0, failed: 0 }`.
  - **metadata**: `null`.
  - **created_at**: `1736472600`.
  - **expires_at**: `1736559000`.
  - **cancelling_at**: `null`.
  - **completed_at**: `null`.
  - **in_progress_at**: `null`.
- **Type**: Object.

## Batch

- **Description**: Returns a batch object.
- **Properties**:
  - **id**: `batch_01jh6xa7reempvjyh6n3yst2zw`.
  - **object**: `batch`.
  - **endpoint**: `/v1/chat/completions`.
  - **errors**: `null`.
  - **input_file_id**: `file_01jh6x76wtemjr74t1fh0faj5t`.
  - **completion_window**: `24h`.
  - **status**: `validating`.
  - **output_file_id**: `null`.
  - **error_file_id**: `null`.
  - **finalizing_at**: `null`.
  - **failed_at**: `null`.
  - **expired_at**: `null`.
  - **cancelled_at**: `null`.
  - **request_counts**: `{ total: 0, completed: 0, failed: 0 }`.
  - **metadata**: `null`.
  - **created_at**: `1736472600`.
  - **expires_at**: `1736559000`.
  - **cancelling_at**: `null`.
  - **completed_at**: `null`.
  - **in_progress_at**: `null`.
- **Type**: Object.

## Batch

- **Description**: Returns a batch object.
- **Properties**:
  - **id**: `batch_01jh6xa7reempvjyh6n3yst2zw`.
  - **object**: `batch`.
  - **endpoint**: `/v1/chat/completions`.
  - **errors**: `null`.
  - **input_file_id**: `file_01jh6x76wtemjr74t1fh0faj5t`.
  - **completion_window**: `24h`.
  - **status**: `validating`.
  - **output_file_id**: `null`.
  - **error_file_id**: `null`.
  - **finalizing_at**: `null`.
  - **failed_at**: `null`.
  - **expired_at**: `null`.
  - **cancelled_at**: `null`.
  - **request_counts**: `{ total: 0, completed: 0, failed: 0 }`.
  - **metadata**: `null`.
  - **created_at**: `1736472600`.
  - **expires_at**: `1736559000`.
  - **cancelling_at**: `null`.
  - **completed_at**: `null`.
  - **in_progress_at**: `null`.
- **Type**: Object.

## Batch

- **Description**: Returns a batch object.
- **Properties**:
  - **id**: `batch_01jh6xa7reempvjyh6n3yst2zw`.
  - **object**: `batch`.
  - **endpoint**: `/v1/chat/completions`.
  - **errors**: `null`.
  - **input_file_id**: `file_01jh6x76wtemjr74t1fh0faj5t`.
  - **completion_window**: `24h`.
  - **status**: `validating`.
  - **output_file_id**: `null`.
  - **error_file_id**: `null`.
  - **finalizing_at**: `null`.
  - **failed_at**: `null`.
  - **expired_at**: `null`.
  - **cancelled_at**: `null`.
  - **request_counts**: `{ total: 0, completed: 0, failed: 0 }`.
  - **metadata**: `null`.
  - **created_at**: `1736472600`.
  - **expires_at**: `1736559000`.
  - **cancelling_at**: `null`.
  - **completed_at**: `null`.
  - **in_progress_at**: `null`.
- **Type**: Object.

## Batch

- **Description**: Returns a batch object.
- **Properties**:
  - **id**: `batch_01jh6xa7reempvjyh6n3yst2zw`.
  - **object**: `batch`.
  - **endpoint**: `/v1/chat/completions`.
  - **errors**: `null`.
  - **input_file_id**: `file_01jh6x76wtemjr74t1fh0faj5t`.
  - **completion_window**: `24h`.
  - **status**: `validating`.
  - **output_file_id**: `null`.
  - **error_file_id**: `null`.
  - **finalizing_at**: `null`.
  - **failed_at**: `null`.
  - **expired_at**: `null`.
  - **cancelled_at**: `null`.
  - **request_counts**: `{ total: 0, completed: 0, failed: 0 }`.
  - **metadata**: `null`.
  - **created_at**: `1736472600`.
  - **expires_at**: `1736559000`.
  - **cancelling_at**: `null`.
  - **completed_at**: `null`.
  - **in_progress_at**: `null`.
- **Type**: Object.

## Batch

- **Description**: Returns a batch object.
- **Properties**:
  - **id**: `batch_01jh6xa7reempvjyh6n3yst2zw`.
  - **object**: `batch`.
  - **endpoint**: `/v1/chat/completions`.
  - **errors**: `null`.
  - **input_file_id**: `file_01jh6x76wtemjr74t1fh0faj5t`.
  - **completion_window**: `24h`.
  - **status**: `validating`.
  - **output_file_id**: `null`.
  - **error_file_id**: `null`.
  - **finalizing_at**: `null`.
  - **failed_at**: `null`.
  - **expired_at**: `null`.
  - **cancelled_at**: `null`.
  - **request_counts**: `{ total: 0, completed: 0, failed: 0 }`.
  - **metadata**: `null`.
  - **created_at**: `1736472600`.
  - **expires_at**: `1736559000`.
  - **cancelling_at**: `null`.
  - **completed_at**: `null`.
  - **in_progress_at**: `null`.
- **Type**: Object.

## Batch

- **Description**: Returns a batch object.
- **Properties**:
  - **id**: `batch_01jh6xa7reempvjyh6n3yst2zw`.
  - **object**: `batch`.
  - **endpoint**: `/v1/chat/completions`.
  - **errors**: `null`.
  - **input_file_id**: `file_01jh6x76wtemjr74t1fh0faj5t`.
  - **completion_window**: `24h`.
  - **status**: `validating`.
  - **output_file_id**: `null`.
  - **error_file_id**: `null`.
  - **finalizing_at**: `null`.
  - **failed_at**: `null`.
  - **expired_at**: `null`.
  - **cancelled_at**: `null`.
  - **request_counts**: `{ total: 0, completed: 0, failed: 0 }`.
  - **metadata**: `null`.
  - **created_at**: `1736472600`.
  - **expires_at**: `1736559000`.
  - **cancelling_at**: `null`.
  - **completed_at**: `null`.
  - **in_progress_at**: `null`.
- **Type**: Object.

## Batch

- **Description**: Returns a batch object.
- **Properties**:
  - **id**: `batch_01jh6xa7reempvjyh6n3yst2zw`.
  - **object**: `batch`.
  - **endpoint**: `/v1/chat/completions`.
  - **errors**: `null`.
  - **input_file_id**: `file_01jh6x76wtemjr74t1fh0faj5t`.
  - **completion_window**: `24h`.

---

# Source: https://docs.groq.com/docs/text-to-speech

# Overview - GroqDocs

## Welcome

Fast LLM inference, OpenAI-compatible. Simple to integrate, easy to scale. Start building in minutes.

## External API Compatibility

- **gemma2-9b-it**
- **llama3-8b-8192**
- **llama3-70b-8192**
- **whisper-large-v3-turbo**
- **whisper-large-v3**
- **llama-guard-3-8b**
- **distil-whisper-large-v3-en**

## Chat Completion

- **Fast language models have gained significant attention in recent years due to their ability to process and generate human-like text quickly and efficiently. The importance of fast language models can be understood from their potential applications and benefits:**
  1. **Real-time Chatbots and Conversational Interfaces**: Fast language models enable the development of chatbots and conversational interfaces that can respond promptly to user queries, making them more engaging and useful.
  2. **Sentiment Analysis and Opinion Mining**: Fast language models can quickly analyze text data to identify sentiments, opinions, and emotions, allowing for improved customer service, market research, and opinion mining.
  3. **Language Translation and Localization**: Fast language models can quickly translate text between languages, facilitating global communication and enabling businesses to reach a broader audience.
  4. **Text Summarization and Generation**: Fast language models can summarize long documents or even generate new text on a given topic, improving information retrieval and processing efficiency.
  5. **Named Entity Recognition and Information Extraction**: Fast language models can rapidly recognize and extract specific entities, such as names, locations, and organizations, from unstructured text data.
  6. **Recommendation Systems**: Fast language models can analyze large amounts of text data to personalize product recommendations, improve customer experience, and increase sales.
  7. **Content Generation for Social Media**: Fast language models can quickly generate engaging content for social media platforms, helping businesses maintain a consistent online presence and increasing their online visibility.
  8. **Sentiment Analysis for Stock Market Analysis**: Fast language models can quickly analyze social media posts, news articles, and other text data to identify sentiment trends, enabling financial analysts to make more informed investment decisions.
  9. **Language Learning and Education**: Fast language models can provide instant feedback and adaptive language learning, making language education more effective and engaging.
  10. **Domain-Specific Knowledge Extraction**: Fast language models can quickly extract relevant information from vast amounts of text data, enabling domain experts to focus on high-level decision-making rather than manual information gathering.

The benefits of fast language models include:
- **Increased Efficiency**: Fast language models can process large amounts of text data quickly, reducing the time and effort required for tasks such as sentiment analysis, entity recognition, and text summarization.
- **Improved Accuracy**: Fast language models can analyze and learn from large datasets, leading to more accurate results and more informed decision-making.
- **Enhanced User Experience**: Fast language models can enable real-time interactions, personalized recommendations, and timely responses, improving the overall user experience.
- **Cost Savings**: Fast language models can automate many tasks, reducing the need for manual labor and minimizing costs associated with data processing and analysis.

In summary, fast language models have the potential to transform various industries and applications by providing fast, accurate, and efficient language processing capabilities.

## Chat Completion Request

- **Description**: A document that can be referenced by the model while generating responses.
- **Properties**:
  - **id**: Optional unique identifier that can be used for citations in responses.
  - **source**: The document containing the text to be referenced by the model.

## Chat Completion Response

- **Description**: A chat completion message generated by the model.
- **Properties**:
  - **annotations**: A list of annotations providing citations and references for the content in the message.
  - **content**: The contents of the message.
  - **executed_tools**: Information about the tools that were executed during the chat completion for compound AI systems.
  - **function_call**: Controls which (if any) function is called by the model.
  - **reasoning**: The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
  - **role**: The role of the messages author, in this case `assistant`.
  - **tool_calls**: The tool calls generated by the model, such as function calls.

## Chat Completion Role

- **Description**: The role of the author of a message.
- **Values**:
  - `system`
  - `user`
  - `assistant`
  - `tool`
  - `developer`

## Chat Completion Stream

- **Description**: A chat completion delta generated by streamed model responses.
- **Properties**:
  - **annotations**: A list of annotations providing citations and references for the content in the message.
  - **content**: The contents of the chunk message.
  - **executed_tools**: Information about the tools that were executed during the chunk.
  - **reasoning**: The model's reasoning for a response. Only available for [models that support reasoning](https://console.groq.com/docs/reasoning) when request parameter reasoning_format has value `parsed`.
  - **role**: The role of the author of this message.
  - **tool_calls**: The tools that were available to the model.

## Chat Completion Token Logprob

- **Description**: A list of tokens with log probability information.
- **Properties**:
  - **bytes**: A list of integers representing the UTF-8 bytes representation of the token.
  - **logprob**: The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely.

## Chat Completion Tool

- **Description**: Describes a tool that the model may call.
- **Properties**:
  - **allowed_tools**: A list of tool names to allow from the MCP server.
  - **function**: Custom model to use for answering.
  - **reasoning_model**: Custom model to use for reasoning.
  - **parameters**: Function parameters defined as a JSON Schema object.

## Chat Completion Function Call

- **Description**: A function call generated by the model.
- **Properties**:
  - **arguments**: A JSON string of the arguments to pass to the function.
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call.
  - **name**: The name of the function to call.
  - **status**: The status of the item.
  - **type**: The type of the function call. Always `function_call`.

## Chat Completion Function Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Chunk

- **Description**: A tool call that this message is responding to.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**:
  - **call_id**: The unique ID of the function tool call generated by the model.
  - **id**: The unique ID of the function tool call output.
  - **output**: A JSON string of the output of the function tool call.
  - **status**: The status of the item.
  - **type**: The type of the function tool call output. Always `function_call_output`.

## Chat Completion Message Tool Call

- **Description**: A tool call generated by the model.
- **Properties**:
  - **function**: Properties of the function to call.
  - **type**: The type of the tool. Always `function`.

## Chat Completion Message Tool Call Output

- **Description**: The output of a function tool call.
- **Properties**