# Aimlapi

> 3D-generating models are AI-powered tools designed to create three-dimensional objects, environments, and textures based on input data such as text prompts, reference images, or existing 3D models. Th

## Pages

- [3D-Generating Models](3d-generating-models.md): 3D-generating models are AI-powered tools designed to create three-dimensional objects, environments, and textures ba...
- [Account Balance](account-balance.md): You can query your account balance and other billing details through this API.\
- [act\_two](act-two.md): {% columns %}
- [Agno](agno.md): [Agno](https://app.agno.com/) is a lightweight library for building **Agents** (AI programs that operate autonomously...
- [AI Search Engine](ai-search-engine.md): AI Web Search Engine is designed to retrieve real-time information from the internet. This solution processes user qu...
- [Aider](aider.md): [Aider](https://aider.chat/) is a command-line pair programming tool that connects to OpenAI-compatible APIs. It lets...
- [Alibaba Cloud](alibaba-cloud.md): - [qwen-max](/api-references/text-models-llm/alibaba-cloud/qwen-max.md)
- [Animate Images: A Children’s Encyclopedia](animate-images-a-childrens-encyclopedia.md): {% hint style="warning" %}
- [Anthracite](anthracite.md): - [magnum-v4](/api-references/text-models-llm/anthracite/magnum-v4.md)
- [Anthropic](anthropic.md): - [Claude 3 Haiku](/api-references/text-models-llm/anthropic/claude-3-haiku.md)
- [Assembly AI](assembly-ai.md): - [slam-1](/api-references/speech-models/speech-to-text/assembly-ai/slam-1.md)
- [aura 2](aura-2.md): Aura 2 produces natural, human-like speech with accurate domain-specific pronunciation — covering drug names, legal t...
- [aura](aura.md): Deepgram Aura is the first text-to-speech (TTS) AI model designed for real-time, conversational AI agents and applica...
- [AutoGPT](autogpt.md): AutoGPT is an open-source platform designed to help you build, test, and run AI agents using a no-code visual interfa...
- [avatar-pro](avatar-pro.md): {% columns %}
- [avatar-standard](avatar-standard.md): {% columns %}
- [BAAI](baai.md): - [bge-base-en](/api-references/embedding-models/baai/bge-base-en.md)
- [Bagoodex](bagoodex.md): - [AI Search Engine](/solutions/bagoodex/ai-search-engine.md): Description, API schema, and usage examples of the spe...
- [Baidu](baidu.md): - [ernie-4.5-8k-preview](/api-references/text-models-llm/baidu/ernie-4.5-8k-preview.md)
- [Batch Processing](batch-processing.md): Batch processing (batching) allows you to send multiple message requests in a single batch and retrieve the results l...
- [bge-base-en](bge-base-en.md): {% columns %}
- [bge-large-en](bge-large-en.md): {% columns %}
- [ByteDance](bytedance.md): - [Seed 1.8](/api-references/text-models-llm/bytedance/seed-1.8.md)
- [Can I call API in the asynchronous mode?](call-api-in-the-asynchronous-mode.md): Sure, any of our available models. Let's see how this works with an example in Python.
- [Can I use API in NodeJS?](can-i-use-api-in-nodejs.md): Yes, definitely! Here is a quick guide on how to start your adventure with AI/ML API in NodeJS.
- [Can I use API in Python?](can-i-use-api-in-python.md): Of course you can! Here is a quick guide on how to configure your environment and use our API.
- [Claude 3 Haiku](claude-3-haiku.md): {% columns %}
- [Claude 3 Opus](claude-3-opus.md): A highly capable multimodal model designed to process both text and image data. It excels in tasks requiring complex ...
- [Claude 3.5 Haiku](claude-35-haiku.md): A cutting-edge model designed for rapid data processing and advanced reasoning capabilities. Excels in coding assista...
- [Claude 3.7 Sonnet](claude-37-sonnet.md): A hybrid reasoning model, designed to tackle complex tasks. It introduces a dual-mode operation, combining standard l...
- [Claude 4.5 Sonnet](claude-4-5-sonnet.md): A major improvement over [Claude 4 Sonnet,](https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-...
- [Claude 4 Opus](claude-4-opus.md): The leading coding model globally, consistently excelling at complex, long-duration tasks and agent-based workflows.
- [Claude 4 Sonnet](claude-4-sonnet.md): A major improvement over [Claude](https://docs.aimlapi.com/api-references/text-models-llm/anthropic/claude-3.7-sonne...
- [Claude 4.5 Haiku](claude-45-haiku.md): The model offers coding performance comparable to [Claude Sonnet 4](https://docs.aimlapi.com/api-references/text-mode...
- [Claude 4.5 Opus](claude-45-opus.md): A high-performance chat model that delivers state-of-the-art results on real-world software engineering benchmarks.
- [Claude 4.1 Opus](claude-opus-41.md): {% hint style="success" %}
- [Cline](cline.md): Cline is an open-source AI coding assistant with two working modes (Plan/Act), terminal command execution, and suppor...
- [Code Generation](code-generation.md): While all text models can write code in various languages upon request, some models are specifically trained for such...
- [Cohere](cohere.md): - [command-a](/api-references/text-models-llm/cohere/command-a.md)
- [command-a](command-a.md): A powerful LLM with advanced capabilities for enterprise applications.
- [Complete Model List](complete-model-list.md): You can query the complete list of available models through this API.\
- [Completion and Chat Completion](completion-or-chat-models.md): This article describes two related capabilities of text models: **completion** and **chat completion**. The former, i...
- [Concepts](concepts.md): API stands for *Application Programming Interface*. In the context of AI/ML, an API serves as a "handle" that enables...
- [continue.dev](continuedev.md): continue.dev is an open-source AI coding assistant that runs directly in your IDE (VS Code, JetBrains, etc). You can ...
- [Create a 3D Model from an Image](create-a-3d-model-from-an-image.md): Transforming a 2D image into a 3D model is a powerful way to bring static visuals to life. Whether you're working on ...
- [Create a Looped GIF for a Web Banner](create-a-looped-gif-for-a-web-banner.md): In this use case, we create an animated banner by combining image generation, video animation, and basic editing. Her...
- [Create an Assistant to Discuss a Specific Document](create-an-assistant-to-discuss-a-specific-document.md): Today, we’re going to create an AI [Assistant](https://docs.aimlapi.com/solutions/openai/assistants) that helps users...
- [Create Images: Illustrate an Article](create-images-illustrate-an-article.md): This workflow allows you to generate an illustration based on a piece of text.
- [Cursor](cursor.md): {% hint style="warning" %}
- [DALL·E 2](dall-e-2.md): {% columns %}
- [DALL·E 3](dall-e-3.md): {% columns %}
- [Deepgram](deepgram.md): - [nova-2](/api-references/speech-models/speech-to-text/deepgram/nova-2.md)
- [DeepSeek Chat V3.1](deepseek-chat-v31.md): {% columns %}
- [DeepSeek V3](deepseek-chat.md): {% columns %}
- [Deepseek Non-reasoner V3.1 Terminus](deepseek-non-reasoner-v31-terminus.md): {% columns %}
- [DeepSeek Prover V2](deepseek-prover-v2.md): {% columns %}
- [DeepSeek R1](deepseek-r1.md): {% columns %}
- [Deepseek Reasoner V3.1 Terminus](deepseek-reasoner-v31-terminus.md): {% columns %}
- [DeepSeek Reasoner V3.1](deepseek-reasoner-v31.md): {% columns %}
- [DeepSeek V3.2 Exp Non-thinking](deepseek-reasoner-v32-exp-non-thinking.md): {% columns %}
- [DeepSeek V3.2 Exp Thinking](deepseek-reasoner-v32-exp-thinking.md): {% columns %}
- [DeepSeek V3.2 Speciale](deepseek-v32-speciale.md): {% columns %}
- [DeepSeek](deepseek.md): - [DeepSeek V3](/api-references/text-models-llm/deepseek/deepseek-chat.md)
- [eleven\_multilingual\_v2](eleven-multilingual-v2.md): {% columns %}
- [eleven\_music](eleven-music.md): {% columns %}
- [eleven\_turbo\_v2\_5](eleven-turbo-v2-5.md): {% columns %}
- [ElevenLabs](elevenlabs.md): - [eleven\_music](/api-references/music-models/elevenlabs/eleven_music.md)
- [ElizaOS](elizaos.md): [ElizaOS](https://eliza.how/docs/intro) is a powerful multi-agent simulation framework designed to create, deploy, an...
- [Embedding Models](embedding-models.md): We support multiple embedding models. You can find the complete list along with AP...
- [ernie-4.5-0.3b](ernie-45-03b.md): {% columns %}
- [ernie-4.5-21b-a3b-thinking](ernie-45-21b-a3b-thinking.md): {% columns %}
- [ernie-4.5-21b-a3b](ernie-45-21b-a3b.md): {% columns %}
- [ernie-4.5-300b-a47b-paddle](ernie-45-300b-a47b-paddle.md): {% columns %}
- [ernie-4.5-300b-a47b](ernie-45-300b-a47b.md): {% columns %}
- [ernie-4.5-8k-preview](ernie-45-8k-preview.md): {% columns %}
- [ernie-4.5-turbo-128k](ernie-45-turbo-128k.md): {% columns %}
- [ernie-4.5-turbo-vl-32k](ernie-45-turbo-vl-32k.md): {% columns %}
- [ernie-4.5-vl-28b-a3b](ernie-45-vl-28b-a3b.md): {% columns %}
- [ernie-4.5-vl-424b-a47b](ernie-45-vl-424b-a47b.md): {% columns %}
- [ernie-5.0-thinking-latest](ernie-50-thinking-latest.md): {% columns %}
- [ernie-5.0-thinking-preview](ernie-50-thinking-preview.md): {% columns %}
- [ernie-x1-turbo-32k](ernie-x1-turbo-32k.md): {% columns %}
- [ernie-x1.1-preview](ernie-x11-preview.md): {% columns %}
- [Errors with status code 4xx](errors-with-status-code-4xx.md): These are client-side errors returned by the AIML API when something is wrong with the request rather than with the s...
- [Errors with status code 5xx](errors-with-status-code-5xx.md): These codes indicate issues on the server side.
- [fabric-1.0-fast](fabric-10-fast.md): {% columns %}
- [fabric-1.0](fabric-10.md): {% columns %}
- [Find a Local Map](find-a-local-map.md): This is a description of one of the six use cases for the AI Search Engine—retrieving a Google Maps link, a small pic...
- [Find Images](find-images.md): This is a description of one of the six use cases for the AI Search Engine model—retrieving internet images related t...
- [Find Links](find-links.md): This is a description of one of the six use cases for this AI Search Engine—retrieving internet links related to the ...
- [Find Relevant Answers: Semantic Search with Text Embeddings](find-relevant-answers-semantic-search-with-text-embeddings.md): Today, we are going to use [text embeddings](https://docs.aimlapi.com/api-references/embedding-models) to transform a...
- [Find the Weather](find-the-weather.md): This is a description of one of the six use cases for the AI Search Engine—retrieving a weather forecast for the requ...
- [Find Videos](find-videos.md): This is a description of one of the six use cases for the AI Search Engine—retrieving internet videos related to the ...
- [flux-2-edit](flux-2-edit.md): {% columns %}
- [flux-2-lora-edit](flux-2-lora-edit.md): {% columns %}
- [flux-2-lora](flux-2-lora.md): {% columns %}
- [flux-2-pro-edit](flux-2-pro-edit.md): {% columns %}
- [flux-2-pro](flux-2-pro.md): {% columns %}
- [flux-2](flux-2.md): {% columns %}
- [flux/dev/image-to-image](flux-dev-image-to-image.md): {% columns %}
- [flux/dev](flux-dev.md): {% columns %}
- [flux/kontext-max/image-to-image](flux-kontext-max-image-to-image.md): {% columns %}
- [flux/kontext-max/text-to-image](flux-kontext-max-text-to-image.md): {% columns %}
- [flux/kontext-pro/image-to-image](flux-kontext-pro-image-to-image.md): {% columns %}
- [flux/kontext-pro/text-to-image](flux-kontext-pro-text-to-image.md): {% columns %}
- [flux-pro/v1.1-ultra](flux-pro-v11-ultra.md): {% columns %}
- [flux-pro/v1.1](flux-pro-v11.md): {% columns %}
- [flux-pro](flux-pro.md): {% columns %}
- [flux-realism](flux-realism.md): {% columns %}
- [flux/schnell](flux-schnell.md): {% columns %}
- [flux/srpo/image-to-image](flux-srpo-image-to-image.md): {% columns %}
- [flux/srpo/text-to-image](flux-srpo-text-to-image.md): {% columns %}
- [Flux](flux.md): Flux, a subsidiary project of Black Forest Labs, is represented in our API by the following models:
- [How to use the Free Tier?](free-tier.md): AIML API has two “free” modes:
- [Function Calling](function-calling.md): This article describes a specific capability of chat models: **function calling**, or simply **functions**.\
- [gemini-2.0-flash-exp](gemini-20-flash-exp.md): A cutting-edge multimodal AI model developed by Google DeepMind, designed to power agentic experiences. This model is...
- [gemini-2.0-flash](gemini-20-flash.md): A cutting-edge multimodal AI model developed by Google DeepMind, designed to power agentic experiences. This model is...
- [Gemini 2.5 Flash Image Edit (Nano Banana)](gemini-25-flash-image-edit.md): {% columns %}
- [Gemini 2.5 Flash Image (Nano Banana)](gemini-25-flash-image.md): {% columns %}
- [gemini-2.5-flash-lite-preview](gemini-25-flash-lite-preview.md): The model excels at high-volume, latency-sensitive tasks like translation and classification.
- [gemini-2.5-flash](gemini-25-flash.md): Gemini 2.5 models are capable of reasoning through their thoughts before responding, resulting in enhanced performanc...
- [gemini-2.5-pro](gemini-25-pro.md): Gemini 2.5 models are capable of reasoning through their thoughts before responding, resulting in enhanced performanc...
- [gemini-3-flash-preview](gemini-3-flash-preview.md): {% columns %}
- [Nano Banana Pro Edit (Gemini 3 Pro Image Edit)](gemini-3-pro-image-preview-edit.md): {% columns %}
- [Nano Banana Pro (Gemini 3 Pro Image)](gemini-3-pro-image-preview.md): {% columns %}
- [gemini-3-pro-preview](gemini-3-pro-preview.md): This model is optimized for advanced agentic tasks, featuring strong reasoning, coding skills, and superior multimoda...
- [gemma-3 (27B)](gemma-3-27b.md): This page describes large variant of Google’s latest open AI model, Gemma 3. In addition to the capabilities of [the ...
- [gemma-3 (4B and 12B)](gemma-3.md): {% hint style="info" %}
- [gemma-3n-4b](gemma-3n-4b.md): The first open model built on Google’s next-generation, mobile-first architecture—designed for fast, private, and mul...
- [gen3a\_turbo](gen3a-turbo.md): {% columns %}
- [gen4\_aleph](gen4-aleph.md): {% columns %}
- [gen4\_turbo](gen4-turbo.md): {% columns %}
- [General Info](general-info.md): This section provides descriptions of the errors a user may encounter when calling our models and solutions via the A...
- [Get a Knowledge Structure](get-a-knowledge-structure.md): This is a description of one of the six use cases for the AI Search Engine—retrieving a small structured knowledge ba...
- [glm-4.5-air](glm-45-air.md): A hybrid reasoning model: features a thinking mode for complex reasoning and tool use, and a non-thinking mode for in...
- [glm-4.5](glm-45.md): A hybrid reasoning model: features a thinking mode for complex reasoning and tool use, and a non-thinking mode for in...
- [glm-4.6](glm-46.md): The latest evolution of the GLM series, glm-4.6 delivers major advancements in coding, long-context understanding, re...
- [glm-4.7](glm-47.md): {% columns %}
- [Google OCR](google-ocr.md): {% hint style="info" %}
- [Google](google.md): - [gemini-2.0-flash-exp](/api-references/text-models-llm/google/gemini-2.0-flash-exp.md)
- [gpt-3.5-turbo](gpt-35-turbo.md): This model builds on the capabilities of earlier versions, offering improved natural language understanding and gener...
- [gpt-4-preview](gpt-4-preview.md): Before the release of GPT-4 Turbo, OpenAI introduced two preview models that allowed users to test advanced features ...
- [gpt-4-turbo](gpt-4-turbo.md): The model enhances the already impressive capabilities of [gpt-4](https://docs.aimlapi.com/api-references/text-models...
- [gpt-4.1-mini](gpt-41-mini.md): {% columns %}
- [gpt-4.1-nano](gpt-41-nano.md): {% columns %}
- [gpt-4.1](gpt-41.md): {% columns %}
- [gpt-4](gpt-4.md): The model represents a significant leap forward in conversational AI technology. It offers enhanced understanding and...
- [gpt-4o-audio-preview](gpt-4o-audio-preview.md): {% columns %}
- [gpt-4o-mini-audio-preview](gpt-4o-mini-audio-preview.md): {% columns %}
- [gpt-4o-mini-search-preview](gpt-4o-mini-search-preview.md): {% columns %}
- [gpt-4o-mini-transcribe](gpt-4o-mini-transcribe.md): {% hint style="info" %}
- [gpt-4o-mini-tts](gpt-4o-mini-tts.md): {% columns %}
- [gpt-4o-mini](gpt-4o-mini.md): OpenAI's latest cost-efficient model designed to deliver advanced natural language processing and multimodal capabili...
- [gpt-4o-search-preview](gpt-4o-search-preview.md): {% columns %}
- [gpt-4o-transcribe](gpt-4o-transcribe.md): {% hint style="info" %}
- [gpt-4o](gpt-4o.md): {% hint style="warning" %}
- [gpt-5.1-chat-latest](gpt-5-1-chat-latest.md): {% columns %}
- [gpt-5.1-codex-mini](gpt-5-1-codex-mini.md): {% columns %}
- [gpt-5.1-codex](gpt-5-1-codex.md): {% columns %}
- [gpt-5.1](gpt-5-1.md): {% columns %}
- [gpt-5-chat](gpt-5-chat.md): {% columns %}
- [gpt-5-mini](gpt-5-mini.md): {% columns %}
- [gpt-5-nano](gpt-5-nano.md): {% columns %}
- [gpt-5-pro](gpt-5-pro.md): {% columns %}
- [gpt-5.2-chat-latest](gpt-52-chat-latest.md): {% columns %}
- [gpt-5.2-codex](gpt-52-codex.md): {% columns %}
- [gpt-5.2-pro](gpt-52-pro.md): {% columns %}
- [gpt-5.2](gpt-52.md): {% columns %}
- [gpt-5](gpt-5.md): {% columns %}
- [gpt-image-1-5](gpt-image-1-5.md): {% columns %}
- [gpt-image-1-5](gpt-image-1-mini-1.md): {% columns %}
- [gpt-image-1-mini](gpt-image-1-mini.md): {% columns %}
- [gpt-image-1](gpt-image-1.md): {% columns %}
- [gpt-oss-120b](gpt-oss-120b.md): {% columns %}
- [gpt-oss-20b](gpt-oss-20b.md): {% columns %}
- [GPT Researcher (gptr)](gpt-researcher-gptr.md): [GPT Researcher](https://docs.gptr.dev/docs/gpt-researcher/getting-started/introduction) is an autonomous agent that ...
- [Grok 2 Image](grok-2-image.md): {% columns %}
- [grok-3-beta](grok-3-beta.md): xAI's most advanced model as of Spring 2025, showcasing superior reasoning capabilities and extensive pretraining kno...
- [grok-3-mini-beta](grok-3-mini-beta.md): A lighter version of the [Grok 3 Beta model](https://docs.aimlapi.com/api-references/text-models-llm/xai/grok-3-beta)...
- [grok-4.1-fast-non-reasoning](grok-4-1-fast-non-reasoning.md): {% columns %}
- [grok-4.1-fast-reasoning](grok-4-1-fast-reasoning.md): xAI’s multimodal model, offering state-of-the-art cost efficiency and a 2M-token context window.\
- [grok-4-fast-non-reasoning](grok-4-fast-non-reasoning.md): xAI’s multimodal model, offering state-of-the-art cost efficiency and a 2M-token context window.\
- [grok-4-fast-reasoning](grok-4-fast-reasoning.md): xAI’s multimodal model, offering state-of-the-art cost efficiency and a 2M-token context window.\
- [grok-4](grok-4.md): Grok 4 is boldly described by its developers as the most intelligent model in the world (as of July 2025).
- [grok-code-fast-1](grok-code-fast-1.md): This model provides rapid, budget-friendly reasoning for agentic coding. By showing reasoning traces in its output, i...
- [Gryphe](gryphe.md): - [MythoMax L2 (13B)](/api-references/text-models-llm/gryphe/mythomax-l2-13b.md)
- [hailuo-02](hailuo-02.md): {% columns %}
- [hailuo-2.3-fast](hailuo-23-fast.md): {% columns %}
- [hailuo-2.3](hailuo-23.md): {% columns %}
- [hermes-4-405b](hermes-4-405b.md): {% columns %}
- [Hume AI](hume-ai.md): - [octave-2](/api-references/speech-models/text-to-speech/hume-ai/octave-2.md)
- [Hunyuan Image v3](hunyuan-image-v3-text-to-image.md): {% columns %}
- [Hunyuan Part](hunyuan-part.md): {% columns %}
- [hunyuan-video-foley](hunyuan-video-foley.md): {% columns %}
- [Image Analysis](image-analysis.md): Some multimodal[^1] text models can recognize various objects, scenes, references, and artistic styles in an image. I...
- [Image Models](image-models.md): Our API features the capability to generate images. We support various models for image generation, including both op...
- [image-o1](image-o1.md): {% columns %}
- [Vision in Text Models (Image-To-Text)](image-to-text-vision.md): This article describes a specific capability of text models: vision, which enables image-to-text conversion. A list o...
- [magic/image-to-video](image-to-video.md): {% columns %}
- [Imagen 3](imagen-30.md): {% columns %}
- [Imagen 4 Fast Generate](imagen-4-fast-generate.md): {% columns %}
- [Imagen 4 Generate](imagen-4-generate.md): {% columns %}
- [Imagen 4 Preview](imagen-4-preview.md): {% columns %}
- [Imagen 4 Ultra Generate](imagen-4-ultra-generate.md): {% columns %}
- [Imagen 4 Ultra Preview](imagen-4-ultra.md): {% columns %}
- [Inworld](inworld.md): - [inworld/tts-1](/api-references/speech-models/text-to-speech/inworld/tts-1.md)
- [Kandinsky 5 Distill (Text-to-Video)](kandinsky5-distill-text-to-video.md): {% columns %}
- [Kandinsky 5 (Text-to-Video)](kandinsky5-text-to-video.md): {% columns %}
- [Kilo Code](kilo-code.md): [Kilo Code](https://kilocode.ai/) is an open-source AI coding assistant and VS Code extension that enables natural-la...
- [kimi-k2-preview](kimi-k2-preview.md): `moonshot/kimi-k2-preview`(July 2025) is a mixture-of-experts model with strong reasoning, coding, and agentic capab...
- [kimi-k2-turbo-preview](kimi-k2-turbo-preview.md): The high-speed version of [Kimi K2](https://docs.aimlapi.com/api-references/text-models-llm/moonshot/kimi-k2-preview)...
- [Kling AI](kling-ai.md): - [image-o1](/api-references/image-models/kling-ai/image-o1.md)
- [krea-wan-14b/text-to-video](krea-wan-14b-text-to-video.md): {% columns %}
- [krea-wan-14b/video-to-video](krea-wan-14b-video-to-video.md): {% columns %}
- [Krea](krea.md): - [krea-wan-14b/text-to-video](/api-references/video-models/krea/krea-wan-14b-text-to-video.md)
- [Langflow](langflow.md): [Langflow](https://www.langflow.org/) is a new visual framework for building multi-agent and RAG applications. It is ...
- [lip-sync](lip-sync.md): {% columns %}
- [LiteLLM](litellm.md): [LiteLLM](https://www.litellm.ai/) is an open-source Python library that provides a unified API for interacting with ...
- [Llama-3-chat-hf](llama-3-chat-hf.md): This model is optimized for dialogue use cases and outperform many existing open-source chat models on common industr...
- [nemotron-nano-12b-v2-vl](llama-31-nemotron-70b-1.md): The model offers strong document understanding and summarization capabilities.
- [llama-3.1-nemotron-70b](llama-31-nemotron-70b.md): A sophisticated LLM, designed to enhance the performance of instruction-following tasks. It utilizes advanced trainin...
- [Llama-3.2-3B-Instruct-Turbo](llama-32-3b-instruct-turbo.md): A large language model (LLM) optimized for instruction-following tasks, striking a balance between computational effi...
- [Llama-3.3-70B-Instruct-Turbo](llama-33-70b-instruct-turbo.md): An optimized language model designed for efficient text generation with advanced features and multilingual support. S...
- [Llama-3.3-70B-Versatile](llama-33-70b-versatile.md): An advanced multilingual large language model with 70 billion parameters, optimized for diverse NLP tasks. It deliver...
- [Llama-4-maverick](llama-4-maverick.md): A 17 billion active parameter model with 128 experts, is the best multimodal model in its class, beating GPT-4o and G...
- [Llama-4-scout](llama-4-scout.md): A 17 billion active parameter model with 16 experts, is the best multimodal model in the world in its class and is mo...
- [Llama-Guard-3-11B-Vision-Turbo](llama-guard-3-11b-vision-turbo.md): {% hint style="info" %}
- [LlamaGuard-2-8b](llamaguard-2-8b.md): {% hint style="info" %}
- [ltxv-2-fast](ltxv-2-fast.md): {% columns %}
- [ltxv-2](ltxv-2.md): {% columns %}
- [LTXV](ltxv.md): - [ltxv-2](/api-references/video-models/ltxv/ltxv-2.md)
- [Luma Ray 1.6 (Text-to-Video)](luma-ai-v2.md): {% columns %}
- [Luma AI](luma-ai.md): The Luma AI Dream Machine API allows developers to generate, retrieve, and extend AI-generated content using a variet...
- [Luma Ray 2](luma-ray-2.md): {% columns %}
- [Luma Ray Flash 2](luma-ray-flash-2.md): {% columns %}
- [Lyria 2](lyria-2.md): {% columns %}
- [m1](m1.md): The world's first open-weight, large-scale hybrid-attention reasoning model.
- [m2-1](m2-1.md): {% columns %}
- [m2-bert-80M-retrieval](m2-bert-80m-retrieval.md): {% columns %}
- [m2](m2.md): A high-performance language model optimized for coding and autonomous agent workflows.
- [Magic](magic.md): - [magic/text-to-video](/api-references/video-models/magic/text-to-video.md)
- [magnum-v4](magnum-v4.md): {% columns %}
- [Make](make.md): Make is a powerful, enterprise-scale automation platform. It offers flow control, data manipulation, HTTP/webhooks, A...
- [Manus](manus.md): [Manus](https://manus.im/docs/introduction/welcome) is a workflow and AI-agent orchestration platform that lets users...
- [Marvin](marvin.md): [Marvin](https://github.com/PrefectHQ/marvin) is a Python framework by PrefectHQ for building agentic AI workflows an...
- [Llama-3-8B-Instruct-Lite](meta-llama-3-8b-instruct-lite.md): A generative text model optimized for dialogue and instruction-following use cases. It leverages a refined transforme...
- [Llama-3.1-405B-Instruct-Turbo](meta-llama-31-405b-instruct-turbo.md): A state-of-the-art large language model developed by Meta AI, designed for advanced text generation tasks. It excels ...
- [Llama-3.1-70B-Instruct-Turbo](meta-llama-31-70b-instruct-turbo.md): A state-of-the-art instruction-tuned language model designed for multilingual dialogue use cases. It excels in natura...
- [Llama-3.1-8B-Instruct-Turbo](meta-llama-31-8b-instruct-turbo.md): An advanced language model designed for high-quality text generation, optimized for professional and industry applica...
- [Meta-Llama-Guard-3-8B](meta-llama-guard-3-8b.md): {% hint style="info" %}
- [Meta](meta.md): - [Llama-3-8B-Instruct-Lite](/api-references/text-models-llm/meta/meta-llama-3-8b-instruct-lite.md)
- [Microsoft](microsoft.md): - [vibevoice-1.5b](/api-references/speech-models/text-to-speech/microsoft/vibevoice-1.5b.md)
- [MiniMax](minimax.md): - [text-01](/api-references/text-models-llm/minimax/text-01.md)
- [Mistral-7B-Instruct](mistral-7b-instruct.md): An advanced version of the Mistral-7B model, fine-tuned specifically for instruction-based tasks. This model is desig...
- [Mistral AI](mistral-ai.md): - [mistral-nemo](/api-references/text-models-llm/mistral-ai/mistral-nemo.md)
- [mistral-nemo](mistral-nemo.md): A state-of-the-art large language model designed for advanced natural language processing tasks, including text gener...
- [mistral-ocr-latest](mistral-ocr-latest.md): {% hint style="info" %}
- [mistral-tiny](mistral-tiny.md): A lightweight language model optimized for efficient text generation, summarization, and code completion tasks. It is...
- [Mixtral-8x7B-Instruct](mixtral-8x7b-instruct-v01.md): A state-of-the-art AI model designed for instruction-following tasks. With a massive 56 billion parameter configurati...
- [All Model IDs](model-database.md): {% hint style="info" %}
- [Content Moderation Models](moderation-safety-models.md): With our API, you can use **content moderation models** (some developers refer to them as "**AI safety models**" or "...
- [Moonshot](moonshot.md): - [kimi-k2-preview](/api-references/text-models-llm/moonshot/kimi-k2-preview.md)
- [music-01](music-01.md): {% columns %}
- [music-1.5](music-15.md): {% columns %}
- [music-2.0](music-20.md): {% columns %}
- [Music Models](music-models.md): Our API features the capability to generate audio. With this API, you can create your own music, speech, and any audi...
- [Are my requests cropped?](my-requests-are-cropped.md): AI/ML API has a parameter called`max_tokens`. Usually, this parameter can be crucial if your requests are large and ...
- [MythoMax L2 (13B)](mythomax-l2-13b.md): {% columns %}
- [n8n](n8n.md): [**n8n**](https://n8n.io/) is an open-source workflow automation tool that lets you connect various services and auto...
- [nemotron-nano-9b-v2](nemotron-nano-9b-v2.md): A unified model designed for both reasoning and non-reasoning tasks. It processes user inputs by first producing a re...
- [NousResearch](nousresearch.md): - [hermes-4-405b](/api-references/text-models-llm/nousresearch/hermes-4-405b.md)
- [nova-2](nova-2.md): {% hint style="info" %}
- [NVIDIA](nvidia.md): - [llama-3.1-nemotron-70b](/api-references/text-models-llm/nvidia/llama-3.1-nemotron-70b.md)
- [o1](o1.md): {% columns %}
- [o3-mini](o3-mini.md): {% columns %}
- [o3-pro](o3-pro.md): {% columns %}
- [o3](o3.md): {% columns %}
- [o4-mini](o4-mini.md): {% columns %}
- [OCR: Optical Character Recognition](ocr-optical-character-recognition.md): Optical Character Recognition (OCR) technology enables the extraction of text from images, scanned documents, and PDF...
- [octave-2](octave-2.md): {% columns %}
- [OFR: Optical Feature Recognition](ofr-optical-feature-recognition.md): Our API provides a feature to extract visual features from images.
- [OmniHuman 1.5](omnihuman-15.md): {% columns %}
- [OmniHuman](omnihuman.md): {% columns %}
- [OpenAI SDK doesn't work?](openai-sdk-doesnt-work.md): Depending on your environment, the steps may differ. For Python and NodeJS, you can proceed to the setup article and ...
- [OpenAI](openai.md): - [gpt-3.5-turbo](/api-references/text-models-llm/openai/gpt-3.5-turbo.md)
- [Our Integration List](our-integration-list.md): Our API endpoint can be integrated with popular AI workflow platforms and tools, allowing their users to access our m...
- [Perplexity](perplexity.md): - [sonar](/api-references/text-models-llm/perplexity/sonar.md)
- [PixVerse](pixverse.md): - [v5/text-to-video](/api-references/video-models/pixverse/v5-text-to-video.md)
- [qwen-image-edit](qwen-image-edit.md): {% columns %}
- [qwen-image](qwen-image.md): {% columns %}
- [qwen-max](qwen-max.md): {% columns %}
- [qwen-plus](qwen-plus.md): {% columns %}
- [qwen-text-embedding-v3](qwen-text-embedding-v3.md): {% columns %}
- [qwen-text-embedding-v4](qwen-text-embedding-v4.md): {% columns %}
- [qwen-turbo](qwen-turbo.md): {% columns %}
- [Qwen2.5-72B-Instruct-Turbo](qwen25-72b-instruct-turbo.md): {% columns %}
- [Qwen2.5-7B-Instruct-Turbo](qwen25-7b-instruct-turbo.md): {% columns %}
- [Qwen2.5-Coder-32B-Instruct](qwen25-coder-32b-instruct.md): {% columns %}
- [qwen3-235b-a22b-thinking-2507](qwen3-235b-a22b-thinking-2507.md): {% columns %}
- [Qwen3-235B-A22B](qwen3-235b-a22b.md): {% columns %}
- [qwen3-32b](qwen3-32b.md): {% columns %}
- [qwen3-coder-480b-a35b-instruct](qwen3-coder-480b-a35b-instruct.md): {% columns %}
- [qwen3-max-instruct](qwen3-max-instruct.md): {% columns %}
- [qwen3-max-preview](qwen3-max-preview.md): {% columns %}
- [qwen3-next-80b-a3b-instruct](qwen3-next-80b-a3b-instruct.md): {% columns %}
- [qwen3-next-80b-a3b-thinking](qwen3-next-80b-a3b-thinking.md): {% columns %}
- [qwen3-omni-30b-a3b-captioner](qwen3-omni-30b-a3b-captioner.md): {% columns %}
- [qwen3-tts-flash](qwen3-tts-flash.md): {% columns %}
- [qwen3-vl-32b-instruct](qwen3-vl-32b-instruct.md): {% columns %}
- [qwen3-vl-32b-thinking](qwen3-vl-32b-thinking.md): {% columns %}
- [Read Text Aloud and Describe Images: Support People with Visual Impairments](read-text-aloud-and-describe-images-ai-tool-to-support-people-with-visual-impair.md): 1. **Upload the PDF to extract all the text**\
- [Documentation Map](readme.md): This page helps you quickly find the right AI model or ready-to-use solution for your task. Open the API reference an...
- [Recraft v3](recraft-v3.md): {% columns %}
- [RecraftAI](recraftai.md): - [Recraft v3](/api-references/image-models/recraftai/recraft-v3.md)
- [reve/create-image](reve-create-image.md): {% columns %}
- [reve/edit-image](reve-edit-image.md): {% columns %}
- [reve/remix-edit-image](reve-remix-edit-image.md): {% columns %}
- [Reve](reve.md): - [reve/create-image](/api-references/image-models/reve/reve-create-image.md)
- [Roo Code](roo-code.md): Roo Code is an autonomous AI programming agent that works right inside your editor, such as VS Code. It helps you cod...
- [Runway](runway.md): - [gen3a\_turbo](/api-references/video-models/runway/gen3a_turbo.md): Description of the gen3a\_turbo model: Pricing,...
- [Sber AI](sber-ai.md): - [Kandinsky 5 (Text-to-Video)](/api-references/video-models/sber-ai/kandinsky5-text-to-video.md)
- [Seed 1.8](seed-18.md): {% columns %}
- [Seedance 1.0 lite (Image-to-Video)](seedance-10-lite-image-to-video.md): {% columns %}
- [Seedance 1.0 lite (Text-to-Video)](seedance-10-lite-text-to-video.md): {% columns %}
- [Seedance 1.0 pro fast](seedance-10-pro-fast.md): {% columns %}
- [Seedance 1.0 pro (Image-to-Video)](seedance-10-pro-image-to-video.md): {% columns %}
- [Seedance 1.0 pro (Text-to-Video)](seedance-10-pro-text-to-video.md): {% columns %}
- [Seededit 3.0 (Image-to-Image)](seededit-30-image-to-image.md): {% columns %}
- [Seedream 3.0](seedream-30.md): {% columns %}
- [Seedream 4.5](seedream-4-5.md): {% columns %}
- [Seedream 4.0 Edit (Image-to-image)](seedream-v4-edit-image-to-image.md): {% columns %}
- [Seedream 4.0 (Text-to-Image)](seedream-v4-text-to-image.md): {% columns %}
- [Service Endpoints](service-endpoints.md): - [Account Balance](/api-references/service-endpoints/account-balance.md)
- [Quickstart](setting-up.md): Here, you'll learn how to start using our API in your code. The following steps must be completed regardless of wheth...
- [Sharpen Generative](sharpen-generative.md): {% columns %}
- [Sharpen](sharpen.md): {% columns %}
- [SillyTavern](sillytavern.md): [SillyTavern](https://github.com/SillyTavern/SillyTavern) is a locally installed user interface that allows you to in...
- [slam-1](slam-1.md): {% columns %}
- [sonar-pro](sonar-pro.md): {% columns %}
- [sonar](sonar.md): {% columns %}
- [sora-2-i2v](sora-2-i2v.md): {% columns %}
- [sora-2-pro-i2v](sora-2-pro-i2v.md): {% columns %}
- [sora-2-pro-t2v](sora-2-pro-t2v.md): {% columns %}
- [sora-2-t2v](sora-2-t2v.md): {% columns %}
- [Speech 2.5 HD Preview](speech-25-hd-preview.md): {% columns %}
- [Speech 2.5 Turbo Preview](speech-25-turbo-preview.md): {% columns %}
- [Speech 2.6 HD](speech-26-hd.md): {% columns %}
- [Speech 2.6 Turbo](speech-26-turbo.md): {% columns %}
- [Voice/Speech Models](speech-models.md): With our API you are able to synthesize speech and transform speech into text.
- [Speech-to-Text](speech-to-text.md): Speech-to-text models convert spoken language into written text, enabling voice-based interactions across various app...
- [Stability AI](stability-ai.md): - [Stable Diffusion v3 Medium](/api-references/image-models/stability-ai/stable-diffusion-v3-medium.md)
- [stable-audio](stable-audio.md): {% columns %}
- [Stable Diffusion v3 Medium](stable-diffusion-v3-medium.md): {% columns %}
- [Stable Diffusion v3.5 Large](stable-diffusion-v35-large.md): {% columns %}
- [Streaming Mode](streaming-mode.md): Streaming mode allows the text chat model to deliver responses as they are generated, rather than waiting for the ent...
- [Summarize Websites with AI-Powered Chrome Extension](summarize-websites-with-ai-powered-chrome-extension.md): In this tutorial, we’ll show how to build a Chrome extension from scratch using an AI/ML API. You’ll set up the devel...
- [Supported SDKs](supported-sdks.md): This page describes the SDK[^1]s that can be used to call our API.
- [Tencent](tencent.md): - [Hunyuan Image v3](/api-references/image-models/tencent/hunyuan-image-v3-text-to-image.md)
- [text-01](text-01.md): A powerful language model developed by MiniMax AI, designed to excel in tasks requiring extensive context processing ...
- [text-embedding-3-large](text-embedding-3-large.md): {% columns %}
- [text-embedding-3-small](text-embedding-3-small.md): {% columns %}
- [text-embedding-ada-002](text-embedding-ada-002.md): {% columns %}
- [Text Models (LLM)](text-models-llm.md): The AI/ML API provides access to text-based models, also known as **Large Language Models** (**LLM**s), and allows yo...
- [text-multilingual-embedding-002](text-multilingual-embedding-002.md): {% columns %}
- [Text-to-Speech](text-to-speech.md): Text-to-speech (TTS) models convert written text into natural-sounding speech, enabling a wide range of applications,...
- [magic/text-to-video](text-to-video.md): {% columns %}
- [Thinking / Reasoning](thinking-reasoning.md): Some text models support advanced reasoning mode, enabling them to perform multi-step problem solving, draw inference...
- [Together AI](together-ai.md): - [m2-bert-80M-retrieval](/api-references/embedding-models/together-ai/m2-bert-80m-retrieval.md)
- [Toolhouse](toolhouse.md): [**Toolhouse**](https://app.toolhouse.ai/) is a Backend-as-a-Service (BaaS) to build, run, and manage AI agents. Tool...
- [Topaz Labs](topaz-labs.md): - [Sharpen](/api-references/image-models/topaz-labs/sharpen.md)
- [triposr](triposr.md): {% columns %}
- [TTS-1 HD](tts-1-hd.md): {% columns %}
- [inworld/tts-1-max](tts-1-max.md): {% columns %}
- [inworld/tts-1](tts-1.md): {% columns %}
- [universal](universal.md): {% columns %}
- [USO (Image-to-Image)](uso.md): {% columns %}
- [v1-pro/image-to-video](v1-pro-image-to-video.md): {% columns %}
- [v1-pro/text-to-video](v1-pro-text-to-video.md): {% columns %}
- [v1-standard/image-to-video](v1-standard-image-to-video.md): {% columns %}
- [v1-standard/text-to-video](v1-standard-text-to-video.md): {% columns %}
- [v1.6-pro/effects](v16-pro-effects.md): {% columns %}
- [v1.6-pro/image-to-video](v16-pro-image-to-video.md): {% columns %}
- [v1.6-pro/text-to-video](v16-pro-text-to-video.md): {% columns %}
- [v1.6-standard/effects](v16-standard-effects.md): {% columns %}
- [v1.6-standard/multi-image-to-video](v16-standard-multi-image-to-video.md): {% columns %}
- [v1.6-standard/text-to-video](v16-standard-text-to-video.md): {% columns %}
- [v1.6-standard/image-to-video](v16-standart-image-to-video.md): {% columns %}
- [v2-master/image-to-video](v2-master-image-to-video.md): {% columns %}
- [v2-master/text-to-video](v2-master-text-to-video.md): {% columns %}
- [v2.1-master/image-to-video](v21-master-image-to-video.md): {% columns %}
- [v2.1-master/text-to-video](v21-master-text-to-video.md): {% columns %}
- [v2.1-pro/image-to-video](v21-pro-image-to-video.md): {% columns %}
- [v2.1-standard/image-to-video](v21-standard-image-to-video.md): {% columns %}
- [v2.5-turbo/pro/image-to-video](v25-turbo-pro-image-to-video.md): {% columns %}
- [v2.5-turbo/pro/text-to-video](v25-turbo-pro-text-to-video.md): {% columns %}
- [v3\_alpha](v3-alpha.md): {% columns %}
- [v5.5/image-to-video](v5-5-image-to-video.md): {% columns %}
- [v5.5/text-to-video](v5-5-text-to-video.md): {% columns %}
- [v5/image-to-video](v5-image-to-video.md): {% columns %}
- [v5/text-to-video](v5-text-to-video.md): {% columns %}
- [v5/transition](v5-transition.md): {% columns %}
- [VEED](veed.md): - [fabric-1.0](/api-references/video-models/veed/fabric-1.0.md)
- [Veo 3.1 Fast (First-Last-Image-to-Video)](veo-3-1-first-last-image-to-video-fast.md): {% columns %}
- [Veo 3.1 (First-Last-Image-to-Video)](veo-3-1-first-last-image-to-video.md): {% columns %}
- [Veo 3.1 Fast (Image-to-Video)](veo-3-1-image-to-video-fast.md): {% columns %}
- [Veo 3.1 (Image-to-Video)](veo-3-1-image-to-video.md): {% columns %}
- [Veo 3.1 (Reference-to-Video)](veo-3-1-reference-to-video.md): {% columns %}
- [Veo 3.1 Fast (Text-to-Video)](veo-3-1-text-to-video-fast.md): {% columns %}
- [Veo 3.1 (Text-to-Video)](veo-3-1-text-to-video.md): {% columns %}
- [Veo 3 Fast (Image-to-Video)](veo-3-fast-image-to-video.md): {% columns %}
- [Veo 3 Fast (Text-to-Video)](veo-3-fast-text-to-video.md): {% columns %}
- [Veo 3 (Image-to-Video)](veo-3-image-to-video.md): {% columns %}
- [Veo 3.1 Extend Video](veo-31-extend-video.md): {% columns %}
- [Veo 3.1 Fast Extend Video](veo-31-fast-extend-video.md): {% columns %}
- [Veo 2 (Image-to-Video)](veo2-image-to-video.md): {% columns %}
- [Veo 2 (Text-to-Video)](veo2-text-to-video.md): {% columns %}
- [Veo 3 (Text-to-Video)](veo3-text-to-video.md): {% columns %}
- [vibevoice-1.5b](vibevoice-15b.md): {% columns %}
- [vibevoice-7b](vibevoice-7b.md): {% columns %}
- [video-01-live2d](video-01-live2d.md): {% columns %}
- [video-01](video-01.md): {% columns %}
- [Video Models](video-models.md): With our API you can generate videos from your prompt and imagination.
- [o1/image-to-video](video-o1-image-to-video.md): {% columns %}
- [o1/reference-to-video](video-o1-reference-to-video.md): {% columns %}
- [o1/video-to-video/edit](video-o1-video-to-video-edit.md): {% columns %}
- [o1/video-to-video-reference](video-o1-video-to-video-reference.md): {% columns %}
- [magic/video-to-video](video-to-video.md): {% columns %}
- [v2.6-pro/text-to-video](video-v2-6-pro-text-to-video.md): {% columns %}
- [v2.6-pro/image-to-video](video-v26-pro-image-to-video.md): {% columns %}
- [v2.6-pro/motion-control](video-v26-pro-motion-control.md): {% columns %}
- [Vision Models](vision-models.md): Our API enables you to use machine learning models for tasks that require visual capabilities. These models are refer...
- [Voice Chat](voice-chat.md): Voice chat models are designed to enable voice-based interactions with AI systems. Unlike traditional text-only assis...
- [voyage-2](voyage-2.md): {% columns %}
- [voyage-code-2](voyage-code-2.md): {% columns %}
- [voyage-finance-2](voyage-finance-2.md): {% columns %}
- [voyage-large-2-instruct](voyage-large-2-instruct.md): {% columns %}
- [voyage-large-2](voyage-large-2.md): {% columns %}
- [voyage-law-2](voyage-law-2.md): {% columns %}
- [voyage-multilingual-2](voyage-multilingual-2.md): {% columns %}
- [wan2.6-image](wan-2-6-image.md): {% columns %}
- [Wan 2.1 Plus (Text-to-Video)](wan-21-plus-text-to-video.md): {% columns %}
- [Wan 2.1 Turbo (Text-to-Video)](wan-21-turbo-text-to-video.md): {% columns %}
- [Wan 2.2 Animate Move (Image-to-Video)](wan-22-14b-animate-move-image-to-video.md): {% columns %}
- [Wan 2.2 Animate Replace (Image-to-Video)](wan-22-14b-animate-replace-image-to-video.md): {% columns %}
- [Wan 2.2 Plus (Text-to-Video)](wan-22-plus-text-to-video.md): {% columns %}
- [Wan 2.5 Preview (Image-to-Video)](wan-25-preview-image-to-video.md): {% columns %}
- [Wan 2.5 Preview (Text-to-Video)](wan-25-preview-text-to-video.md): {% columns %}
- [Wan 2.6 (Image-to-Video)](wan-26-image-to-video.md): {% columns %}
- [Wan 2.6 (Reference-to-Video)](wan-26-reference-to-video.md): {% columns %}
- [Wan 2.6 (Text-to-Video)](wan-26-text-to-video.md): {% columns %}
- [wan2.2-t2i-flash](wan22-t2i-flash.md): {% columns %}
- [wan2.2-t2i-plus](wan22-t2i-plus.md): {% columns %}
- [Wan 2.2 VACE Fun Depth (Image-to-Video)](wan22-vace-fun-a14b-depth-image-to-video.md): {% columns %}
- [Wan 2.2 VACE Fun Inpainting (Image-to-Video)](wan22-vace-fun-a14b-inpainting-image-to-video.md): {% columns %}
- [Wan 2.2 VACE Fun Outpainting (Image-to-Video)](wan22-vace-fun-a14b-outpainting-image-to-video.md): {% columns %}
- [Wan 2.2 VACE Fun Pose (Image-to-Video)](wan22-vace-fun-a14b-pose-image-to-video.md): {% columns %}
- [Wan 2.2 VACE Fun Reframe (Image-to-Video)](wan22-vace-fun-a14b-reframe-image-to-video.md): {% columns %}
- [wan2.5-t2i-preview](wan25-t2i-preview.md): {% columns %}
- [Web Search](web-search.md): This capability of text chat models allows them to send search queries to the web, retrieve relevant content, and use...
- [whisper-base](whisper-base.md): {% hint style="info" %}
- [whisper-large](whisper-large.md): {% hint style="info" %}
- [whisper-medium](whisper-medium.md): {% hint style="info" %}
- [whisper-small](whisper-small.md): {% hint style="info" %}
- [whisper-tiny](whisper-tiny.md): {% hint style="info" %}
- [xAI](xai.md): - [grok-3-beta](/api-references/text-models-llm/xai/grok-3-beta.md)
- [z-image-turbo-lora](z-image-turbo-lora.md): {% columns %}
- [z-image-turbo](z-image-turbo.md): {% columns %}
- [Zhipu](zhipu.md): - [glm-4.5-air](/api-references/text-models-llm/zhipu/glm-4.5-air.md)