# Fireworks Ai

> Build production-ready AI agents with Fireworks and leading open-source frameworks

## Pages

- [Agent Frameworks](agent-frameworks.md): Build production-ready AI agents with Fireworks and leading open-source frameworks
- [firectl alias evaluator-revision](alias-evaluator-revision.md): Alias an evaluator revision
- [Are there any quotas for serverless?](are-there-any-quotas-for-serverless.md): Yes, serverless deployments have rate limits and quotas.
- [Are there discounts for bulk usage?](are-there-discounts-for-bulk-usage.md): We offer discounts for bulk or pre-paid purchases. Contact [inquiries@fireworks.ai](mailto:inquiries@fireworks.ai) to...
- [Are there extra fees for serving fine-tuned models?](are-there-extra-fees-for-serving-fine-tuned-models.md): No, deploying fine-tuned models to serverless infrastructure is free. Here's what you need to know:
- [Streaming Transcription](audio-streaming-transcriptions.md): Streaming transcription is performed over a WebSocket. Provide the transcription parameters and establish a WebSocket...
- [Transcribe audio](audio-transcriptions.md): Send a sample audio to get a transcription.
- [Translate audio](audio-translations.md): Your Fireworks API key, e.g.`Authorization=API_KEY`.
- [Audit & Access Logs](audit-logs.md): Monitor and track account activities with audit logging for Enterprise accounts
- [Authentication](authentication.md): Authentication for access to your account
- [Autoscaling](autoscaling.md): Configure how your deployment scales based on traffic
- [Batch Delete Batch Jobs](batch-delete-batch-jobs.md): paths:
- [Batch Delete Environments](batch-delete-environments.md): paths:
- [Batch Delete Node Pools](batch-delete-node-pools.md): paths:
- [Batch API](batch-inference.md): Process large-scale async workloads
- [Performance benchmarking](benchmarking.md): Measure and optimize your deployment's performance with load testing
- [Cancel Batch Job](cancel-batch-job.md): Cancels an existing batch job if it is queued, pending, or running.
- [firectl cancel dpo-job](cancel-dpo-job.md): Cancels a running dpo job.
- [Cancel Reinforcement Fine-tuning Job](cancel-reinforcement-fine-tuning-job.md): paths:
- [firectl cancel supervised-fine-tuning-job](cancel-supervised-fine-tuning-job.md): Cancels a running supervised fine-tuning job.
- [Changelog](changelog.md): The evaluator creation workflow has been significantly enhanced with GitHub template integration. You can now:
- [Training Guide: CLI](cli-reference.md): Launch RFT jobs using the eval-protocol CLI
- [Client-side performance optimization](client-side-performance-optimization.md): Optimize your client code for maximum performance with dedicated deployments
- [Completions API](completions-api.md): Use the completions API for raw text generation with custom prompt templates
- [Concepts](concepts.md): This document outlines basic Fireworks AI concepts.
- [Connect Environment](connect-environment.md): Connects the environment to a node pool.
- [Remote Environment Setup](connect-environments.md): Implement the /init endpoint to run evaluations in your infrastructure
- [Cookbooks](cookbooks.md): Interactive Jupyter notebooks demonstrating advanced use cases and best practices with Fireworks AI
- [Create API Key](create-api-key.md): paths:
- [Create Aws Iam Role Binding](create-aws-iam-role-binding.md): paths:
- [Create Batch Inference Job](create-batch-inference-job.md): paths:
- [Create Batch Job](create-batch-job.md): paths:
- [Create Batch Request](create-batch-request.md): Create a batch request for our audio transcription service
- [Create Cluster](create-cluster.md): paths:
- [Create Dataset](create-dataset.md): paths:
- [Load LoRA](create-deployed-model.md): paths:
- [Create Deployment](create-deployment.md): paths:
- [null](create-dpo-job.md): paths:
- [Create Environment](create-environment.md): paths:
- [Create Evaluation Job](create-evaluation-job.md): openapi: 3.1.0
- [Create Evaluator](create-evaluator.md): Creates a custom evaluator for scoring model outputs. Evaluators use the
- [firectl create identity-provider](create-identity-provider.md): Creates a new identity provider.
- [Create Model](create-model.md): paths:
- [Create Node Pool Binding](create-node-pool-binding.md): paths:
- [Create Node Pool](create-node-pool.md): paths:
- [Create Reinforcement Fine-tuning Job](create-reinforcement-fine-tuning-job.md): paths:
- [Create Reinforcement Fine-tuning Step](create-reinforcement-fine-tuning-step.md): paths:
- [null](create-secret.md): paths:
- [Create Snapshot](create-snapshot.md): paths:
- [Create Supervised Fine-tuning Job](create-supervised-fine-tuning-job.md): paths:
- [Create User](create-user.md): paths:
- [Create embeddings](creates-an-embedding-vector-representing-the-input-text.md): paths:
- [Zero Data Retention](data-handling.md): Data retention policies at Fireworks
- [Data Security](data-security.md): How we secure and handle your data for inference and training
- [Delete API Key](delete-api-key.md): paths:
- [Delete Aws Iam Role Binding](delete-aws-iam-role-binding.md): paths:
- [Delete Batch Inference Job](delete-batch-inference-job.md): paths:
- [Delete Batch Job](delete-batch-job.md): paths:
- [Delete Cluster](delete-cluster.md): paths:
- [Delete Dataset](delete-dataset.md): paths:
- [Unload LoRA](delete-deployed-model.md): paths:
- [Delete Deployment](delete-deployment.md): paths:
- [null](delete-dpo-job.md): paths:
- [Delete Environment](delete-environment.md): paths:
- [Delete Evaluation Job](delete-evaluation-job.md): openapi: 3.1.0
- [firectl delete evaluator-revision](delete-evaluator-revision.md): Delete an evaluator revision
- [Delete Evaluator](delete-evaluator.md): Deletes an evaluator and its associated versions and build artifacts.
- [Delete Model](delete-model.md): paths:
- [Delete Node Pool Binding](delete-node-pool-binding.md): paths:
- [Delete Node Pool](delete-node-pool.md): paths:
- [Delete Reinforcement Fine-tuning Job](delete-reinforcement-fine-tuning-job.md): paths:
- [Delete Reinforcement Fine-tuning Step](delete-reinforcement-fine-tuning-step.md): paths:
- [Delete Response](delete-response.md): Deletes a model response by its ID. Once deleted, the response data will be gone immediately and permanently.
- [null](delete-secret.md): paths:
- [Delete Snapshot](delete-snapshot.md): paths:
- [Delete Supervised Fine-tuning Job](delete-supervised-fine-tuning-job.md): paths:
- [firectl delete user](delete-user.md): Deletes a user.
- [Deploying Fine Tuned Models](deploying-loras.md): Deploy one or multiple LoRA models fine tuned on Fireworks
- [Direct routing](direct-routing.md): Direct routing enables enterprise users reduce latency to their deployments.
- [Disconnect Environment](disconnect-environment.md): Disconnects the environment from the node pool. Returns an error
- [Do you provide notice before removing model availability?](do-you-provide-notice-before-removing-model-availability.md): Yes, we provide advance notice before removing models from the serverless infrastructure:
- [Do you support Auto Scaling?](do-you-support-auto-scaling.md): Yes, our system supports **auto scaling** with the following features:
- [Does Fireworks support custom base models?](does-fireworks-support-custom-base-models.md): Yes, custom base models can be deployed via **firectl**. You can learn more about custom model deployment in our [gui...
- [Does the API support batching and load balancing?](does-the-api-support-batching-and-load-balancing.md): Current capabilities include:
- [firectl download billing-metrics](download-billing-metrics.md): Exports billing metrics
- [firectl download dataset](download-dataset.md): Downloads a dataset to a local directory.
- [firectl download dpo-job-metrics](download-dpo-job-metrics.md): Retrieves metrics for a dpo job.
- [firectl download model](download-model.md): Download a model.
- [Direct Preference Optimization](dpo-fine-tuning.md): Direct Preference Optimization (DPO) fine-tunes models by training them on pairs of preferred and non-preferred respo...
- [Agent Tracing](environments.md): Understand where your agent runs and how tracing enables reinforcement fine-tuning
- [Evaluators](evaluators.md): Understand the fundamentals of evaluators and reward functions in reinforcement fine-tuning
- [Execute one training step for keep-alive Reinforcement Fine-tuning Step](execute-reinforcement-fine-tuning-step.md): openapi: 3.1.0
- [Exporting Billing Metrics](exporting-billing-metrics.md): Export billing and usage metrics for all Fireworks services
- [Exporting Metrics](exporting-metrics.md): Export metrics from your dedicated deployments to your observability stack
- [Supervised Fine Tuning - Text](fine-tuning-models.md): This guide will focus on using supervised fine-tuning to fine-tune and deploy a model with on-demand and serverless h...
- [Supervised Fine Tuning - Vision](fine-tuning-vlm.md): Learn how to fine-tune vision-language models on Fireworks AI with image and text datasets
- [Fine Tuning Overview](finetuning-intro.md): Fireworks helps you fine-tune models to improve quality and performance for your product use cases, without the burde...
- [Getting started](firectl.md): Learn to create, deploy, and manage resources using Firectl
- [FLUX image generation](flux-image-generation.md): No, FLUX serverless supports only one image per API call. For multiple images, send separate parallel requests—these ...
- [Tool Calling](function-calling.md): Connect models to external tools and APIs
- [Generate or edit an image with FLUX.1 Kontext](generate-or-edit-image-using-flux-kontext.md): 💡 Note that this API is async and will return the **request\_id** instead of the image. Call the [get\_result](/api-r...
- [Get Account](get-account.md): paths:
- [Get Batch Inference Job](get-batch-inference-job.md): paths:
- [Get Batch Job Logs](get-batch-job-logs.md): paths:
- [Get Batch Job](get-batch-job.md): paths:
- [Check Batch Status](get-batch-status.md): This endpoint allows you to check the current status of a previously submitted batch request, and retrieve the final ...
- [Get Cluster Connection Info](get-cluster-connection-info.md): Retrieve connection settings for the cluster to be put in kubeconfig
- [Get Cluster](get-cluster.md): paths:
- [Get Dataset Download Endpoint](get-dataset-download-endpoint.md): paths:
- [Get Dataset Upload Endpoint](get-dataset-upload-endpoint.md): paths:
- [Get Dataset](get-dataset.md): paths:
- [Get LoRA](get-deployed-model.md): paths:
- [Get Deployment Shape Version](get-deployment-shape-version.md): paths:
- [Get Deployment Shape](get-deployment-shape.md): openapi: 3.1.0
- [Get Deployment](get-deployment.md): paths:
- [null](get-dpo-job-metrics-file-endpoint.md): paths:
- [null](get-dpo-job.md): paths:
- [Get Environment](get-environment.md): paths:
- [Get Evaluation Job execution logs (stream log endpoint + tracing IDs).](get-evaluation-job-log-endpoint.md): openapi: 3.1.0
- [Get Evaluation Job](get-evaluation-job.md): openapi: 3.1.0
- [Get Evaluator Build Log Endpoint](get-evaluator-build-log-endpoint.md): Returns a signed URL to download the evaluator's build logs. Useful for
- [firectl get evaluator-revision](get-evaluator-revision.md): Get an evaluator revision
- [Get Evaluator Source Code Endpoint](get-evaluator-source-code-endpoint.md): Returns a signed URL to download the evaluator's source code archive.
- [Get Evaluator Upload Endpoint](get-evaluator-upload-endpoint.md): Returns signed URLs for uploading evaluator source code (**step 3** in the
- [Get Evaluator](get-evaluator.md): Retrieves an evaluator by name. Use this to monitor build progress after
- [firectl get feature-flag](get-feature-flag.md): Gets a feature flag.
- [Get generated image from FLUX.1 Kontext](get-generated-image-from-flux-kontex.md): Replace **model** with **flux-kontext-pro** in the API to get the result.
- [firectl get identity-provider](get-identity-provider.md): Prints information about an identity provider.
- [Get Model Download Endpoint](get-model-download-endpoint.md): paths:
- [Get Model Upload Endpoint](get-model-upload-endpoint.md): paths:
- [Get Model](get-model.md): paths:
- [Get Node Pool Stats](get-node-pool-stats.md): paths:
- [Get Node Pool](get-node-pool.md): paths:
- [firectl get quota](get-quota.md): Prints information about a quota.
- [Get Reinforcement Fine-tuning Job](get-reinforcement-fine-tuning-job.md): paths:
- [Get Reinforcement Fine-tuning Step](get-reinforcement-fine-tuning-step.md): paths:
- [firectl get reservation](get-reservation.md): Prints information about a reservation.
- [Get Response](get-response.md): paths:
- [Get Secret](get-secret.md): Retrieves a secret by name. Note that the`value`field is not returned in the response for security reasons. Only th...
- [Get Snapshot](get-snapshot.md): paths:
- [Get Supervised Fine-tuning Job](get-supervised-fine-tuning-job.md): paths:
- [Get User](get-user.md): paths:
- [How do I close my Fireworks.ai account?](how-do-i-close-my-fireworksai-account.md): To close your account:
- [How do I control output image sizes when using SDXL ControlNet?](how-do-i-control-output-image-sizes-when-using-sdxl-controlnet.md): When using **SDXL ControlNet** (e.g., canny control), the output image size is determined by the explicit **width** a...
- [How does autoscaling affect my costs?](how-does-autoscaling-affect-my-costs.md): * **Scaling from 0**: No minimum cost when scaled to zero
- [How does billing and credit usage work?](how-does-billing-and-credit-usage-work.md): Usage and billing operate through a **tiered system**:
- [How does billing and scaling work for on-demand GPU deployments?](how-does-billing-and-scaling-work-for-on-demand-gpu-deployments.md): On-demand GPU deployments have unique billing and scaling characteristics compared to serverless deployments:
- [How does billing work for on-demand deployments?](how-does-billing-work-for-on-demand-deployments.md): On-demand deployments come with automatic cost optimization features:
- [How does the system scale?](how-does-the-system-scale.md): Our system is **horizontally scalable**, meaning it:
- [How many tokens per image?](how-many-tokens-per-image.md): Learn how to calculate token usage for images in vision models and understand pricing implications
- [How much does Fireworks cost?](how-much-does-fireworks-cost.md): Fireworks AI operates on a **pay-as-you-go** model for all non-Enterprise usage, and new users automatically receive ...
- [Basics](how-rft-works.md): Understand the reinforcement learning fundamentals behind RFT
- [How to check if a model is available on serverless?](how-to-check-if-a-model-is-available-on-serverless.md): Go to [
- [I have multiple Fireworks accounts. When I try to login with Google on Fireworks' web UI, I'm getting signed into the wrong account. How do I fix this?](i-have-multiple-fireworks-accounts-when-i-try-to-login-with-google-on-fireworks.md): If you log in with Google, account management is controlled by Google. You can log in through an incognito mode or cr...
- [Inference Error Codes](inference-error-codes.md): Common error codes, their meanings, and resolutions for inference requests
- [Cloud Integrations](integrations.md): Cloud Integrations
- [Introduction](introduction.md): Fireworks AI REST API enables you to interact with various language, image and embedding models using an API Key. It ...
- [Are there SLAs for serverless?](is-latency-guaranteed-for-serverless-models.md): Our multi-tenant serverless offering does not currently come with Service Level Agreements (SLAs) for latency or avai...
- [Is prompt caching billed differently for serverless models?](is-prompt-caching-billed-differently.md): No, **prompt caching does not affect billing for serverless models**. You are charged the same amount regardless of w...
- [List Accounts](list-accounts.md): paths:
- [firectl list api-key](list-api-key.md): Prints all API keys for the signed in user.
- [List API Keys](list-api-keys.md): paths:
- [List Aws Iam Role Bindings](list-aws-iam-role-bindings.md): paths:
- [List Batch Inference Jobs](list-batch-inference-jobs.md): paths:
- [List Batch Jobs](list-batch-jobs.md): paths:
- [List Clusters](list-clusters.md): paths:
- [firectl list credit-redemptions](list-credit-redemptions.md): Lists credit code redemptions for the current account.
- [List Datasets](list-datasets.md): paths:
- [List LoRAs](list-deployed-models.md): paths:
- [List Deployment Shapes Versions](list-deployment-shape-versions.md): paths:
- [List Deployment Shapes](list-deployment-shapes.md): openapi: 3.1.0
- [List Deployments](list-deployments.md): paths:
- [null](list-dpo-jobs.md): paths:
- [List Environments](list-environments.md): paths:
- [List Evaluation Jobs](list-evaluation-jobs.md): openapi: 3.1.0
- [firectl list evaluator-revisions](list-evaluator-revisions.md): List evaluator revisions
- [List Evaluators](list-evaluators.md): Lists all evaluators for an account with pagination support.
- [firectl list identity-providers](list-identity-providers.md): List identity providers for an account
- [firectl list invoices](list-invoices.md): Prints information about invoices.
- [List Models](list-models.md): paths:
- [List Node Pool Bindings](list-node-pool-bindings.md): paths:
- [List Node Pools](list-node-pools.md): paths:
- [firectl list quotas](list-quotas.md): Prints all quotas.
- [List Reinforcement Fine-tuning Jobs](list-reinforcement-fine-tuning-jobs.md): paths:
- [List Reinforcement Fine-tuning Steps](list-reinforcement-fine-tuning-steps.md): paths:
- [firectl list reservations](list-reservations.md): Prints active reservations.
- [List Responses](list-responses.md): Get a list of all responses for the authenticated account.
- [firectl list secret](list-secret.md): Lists all secrets for the signed in user.
- [List Secrets](list-secrets.md): Lists all secrets for an account. Note that the`value`field is not returned in the response for security reasons. O...
- [List Snapshots](list-snapshots.md): paths:
- [List Supervised Fine-tuning Jobs](list-supervised-fine-tuning-jobs.md): paths:
- [firectl list user](list-user.md): Prints all users in the account.
- [List Users](list-users.md): paths:
- [firectl load-lora](load-lora.md): Loads a LoRA model to a deployment.
- [MLOps & Observability](mlops-observability.md): Track and monitor your Fireworks AI deployments with leading MLOps and observability platforms
- [Monitor Training](monitor-training.md): Track RFT job progress and diagnose issues in real-time
- [Deployments](ondemand-deployments.md): Configure and manage on-demand deployments on dedicated GPUs
- [Deployments Quickstart](ondemand-quickstart.md): Deploy models on dedicated GPUs in minutes
- [OpenAI compatibility](openai-compatibility.md): You can use the [OpenAI Python client library](https://github.com/openai/openai-python) to interact with Fireworks. T...
- [Parameter Tuning](parameter-tuning.md): Learn how training parameters affect model behavior and outcomes
- [Create Chat Completion](post-chatcompletions.md): Creates a model response for the given chat conversation.
- [Create Completion](post-completions.md): Creates a completion for the provided prompt and parameters.
- [Create Response](post-responses.md): Creates a model response, optionally interacting with custom tools via the Model Context Protocol (MCP). This endpoin...
- [Using predicted outputs](predicted-outputs.md): Use Predicted Outputs to boost output generation speeds for editing / rewriting use cases
- [Prepare Model for different precisions](prepare-model.md): paths:
- [Prompt caching](prompt-caching.md): Prompt caching is a performance optimization feature that allows Fireworks to
- [Python SDK](python-sdk.md): The official Python SDK for the Fireworks AI API is available on [GitHub](https://github.com/fw-ai-external/python-sd...
- [Quantization](quantization.md): Reduce model precision to improve performance and lower costs
- [Speech to Text](querying-asr-models.md): Convert audio to text with streaming and pre-recorded transcription
- [Querying Dedicated Deployments](querying-dedicated-deployments.md): Learn how to connect to and query dedicated deployments that were created outside the SDK
- [Embeddings & Reranking](querying-embeddings-models.md): Generate embeddings and rerank results for semantic search
- [Text Models](querying-text-models.md): Query, track and manage inference for text models
- [Vision Models](querying-vision-language-models.md): Query vision-language models to analyze images and visual content
- [Single-Turn Training Quickstart](quickstart-math.md): Train a model to be an expert at answering GSM8K math questions
- [Remote Agent Quickstart](quickstart-svg-agent.md): Train an SVG drawing agent running in a remote environment
- [Serverless Quickstart](quickstart.md): Make your first Serverless API call in minutes
- [Rate Limits & Quotas](rate-limits.md): Understand and manage your rate limits, spend limits and quotas
- [Reasoning](reasoning.md): How to use reasoning with Fireworks models
- [Which model should I use?](recommended-models.md): Find the best open models for your use case or migrate from closed source models like Claude, GPT, and Gemini
- [firectl redeem-credit-code](redeem-credit-code.md): Redeems a credit code for the current account.
- [Regions](regions.md): Fireworks runs a global fleet of hardware on which you can deploy your models.
- [Overview](reinforcement-fine-tuning-models.md): Train models using reinforcement learning in minutes
- [Rerank documents](rerank-documents.md): Rerank documents for a query using relevance scoring
- [Reserved capacity](reservations.md): Enterprise accounts can purchase reserved capacity, typically with 1 year commitments. Reserved capacity has the foll...
- [Responses API](response-api.md): Fireworks.ai offers a powerful Responses API that allows for more complex and stateful interactions with models. This...
- [Resume Dpo Job](resume-dpo-job.md): openapi: 3.1.0
- [Resume Reinforcement Fine-tuning Job](resume-reinforcement-fine-tuning-job.md): paths:
- [Resume Rlor Trainer Job](resume-reinforcement-fine-tuning-step.md): openapi: 3.1.0
- [Resume Supervised Fine-tuning Job](resume-supervised-fine-tuning-job.md): paths:
- [Parameters Reference](rft-parameters-reference.md): Quick lookup for all RFT training and rollout parameters
- [firectl rollback evaluator](rollback-evaluator.md): Rollback an evaluator to a specific revision
- [Scale Deployment to a specific number of replicas or to zero](scale-deployment.md): paths:
- [firectl scale](scale.md): Scales a deployment to a specified number of replicas.
- [Build SDK Basics](sdk-basics.md): This SDK documentation applies to version [0.19.20](https://pypi.org/project/fireworks-ai/0.19.20/) and earlier. The ...
- [Build SDK Introduction](sdk-introduction.md): This SDK documentation applies to version [0.19.20](https://pypi.org/project/fireworks-ai/0.19.20/) and earlier. The ...
- [Reference](sdk-reference.md): This SDK documentation applies to version [0.19.20](https://pypi.org/project/fireworks-ai/0.19.20/) and earlier. The ...
- [Secure Training (BYOB)](secure-fine-tuning.md): Fine-tune models while keeping sensitive data and components under your control
- [Service Accounts](service-accounts.md): How to manage and use service accounts in Fireworks
- [firectl set-api-key](set-api-key.md): Sets the default API key in ~/.fireworks/auth.ini.
- [Speculative Decoding](speculative-decoding.md): Speed up generation with draft models and n-gram speculation
- [Custom SSO](sso.md): Set up custom Single Sign-On (SSO) authentication for Fireworks AI
- [Structured Outputs](structured-response-formatting.md): Enforce output formats using JSON schemas or custom grammars
- [Tutorial](the-tutorial.md): This SDK documentation applies to version [0.19.20](https://pypi.org/project/fireworks-ai/0.19.20/) and earlier. The ...
- [There’s a model I would like to use that isn’t available on Fireworks. Can I request it?](theres-a-model-i-would-like-to-use-that-isnt-available-on-fireworks-can-i-reques.md): Fireworks supports a wide array of custom models and actively takes feature requests for new, popular models to add t...
- [Training Prerequisites & Validation](training-prerequisites.md): Requirements, validation checks, and common issues when launching RFT jobs
- [Undelete Deployment](undelete-deployment.md): paths:
- [firectl unload-lora](unload-lora.md): Unloads a LoRA model from a deployment.
- [Update Batch Job](update-batch-job.md): paths:
- [Update Cluster](update-cluster.md): paths:
- [Update Dataset](update-dataset.md): paths:
- [Update LoRA](update-deployed-model.md): paths:
- [Update Deployment](update-deployment.md): paths:
- [Update Environment](update-environment.md): paths:
- [Update Evaluator](update-evaluator.md): Updates evaluator metadata (display_name, description, default_dataset).
- [Update Model](update-model.md): paths:
- [Update Node Pool](update-node-pool.md): paths:
- [firectl update quota](update-quota.md): Updates a quota.
- [null](update-secret.md): paths:
- [Update User](update-user.md): paths:
- [firectl upgrade](upgrade.md): Upgrades the firectl binary to the latest version.
- [Upload Dataset Files](upload-dataset-files.md): Provides a streamlined way to upload a dataset file in a single API request. This path can handle file sizes up to 15...
- [firectl upload model](upload-model.md): Resumes or completes a model upload.
- [Custom Models](uploading-custom-models.md): Upload, verify, and deploy your own models from Hugging Face or elsewhere
- [Managing users](users.md): Add and delete additional users in your Fireworks account
- [Using Secrets](using-secret-in-evaluator.md): Learn how to create secrets that can be utilized within your reward function.
- [Validate Dataset Upload](validate-dataset-upload.md): paths:
- [Validate Evaluator Upload](validate-evaluator-upload.md): Triggers server-side validation of the uploaded source code (**step 5** in
- [Validate Model Upload](validate-model-upload.md): paths:
- [firectl version](version.md): Prints the version of firectl
- [Training Guide: UI](web-ui-guide.md): Launch RFT jobs using the Fireworks dashboard
- [What are the rate limits for on-demand deployments?](what-are-the-rate-limits-for-on-demand-deployments.md): On-demand deployments have GPU quotas that determine your maximum allocation.
- [What email does GitHub authentication use?](what-email-does-github-authentication-use.md): When you authenticate with Fireworks using GitHub, we use the **primary email address** associated with your GitHub a...
- [What email does LinkedIn authentication use?](what-email-does-linkedin-authentication-use.md): When you authenticate with Fireworks using LinkedIn, we use the **primary email address** associated with your Linked...
- [What factors affect the number of simultaneous requests that can be handled?](what-factors-affect-the-number-of-simultaneous-requests-that-can-be-handled.md): The request handling capacity is influenced by multiple factors:
- [How do credits work?](what-happens-when-i-finish-my-1-dollar-credit.md): Fireworks operates with a **postpaid billing** system:
- [What should I do if I can't access my company account after being invited when I already have a personal account?](what-should-i-do-if-i-cant-access-my-company-account-after-being-invited-when-i.md): This issue can occur when you have multiple accounts associated with the same email address (e.g., a personal account...
- [What’s the supported throughput?](whats-the-supported-throughput.md): Throughput capacity typically depends on several factors:
- [firectl whoami](whoami.md): Shows the currently authenticated user
- [Why am I experiencing request timeout errors and slow response times with serverless LLM models?](why-am-i-experiencing-request-timeout-errors-and-slow-response-times-with-server.md): Timeout errors and increased response times can occur due to **server load during high-traffic periods**.
- [Why might my account be suspended even with remaining credits?](why-might-my-account-be-suspended-even-with-remaining-credits.md): Your account may be suspended due to several factors: