# FastRouter.AI Docs ## FastRouter Docs - [Welcome](https://docs.fastrouter.ai/readme.md): Welcome to FastRouter.AI! - [Dashboard](https://docs.fastrouter.ai/explore-features/quickstart.md): The Dashboard and Activity Log are essential for monitoring, analyzing, and optimizing your API usage with large language models (LLMs). - [Automatic Model Selection](https://docs.fastrouter.ai/explore-features/automatic-model-selection.md) - [Virtual Model Aliases](https://docs.fastrouter.ai/explore-features/virtual-model-aliases.md): Virtual Model Aliases make it easy to manage and optimize amongst multiple LLMs without changing your code. - [FastRouter Blend: Multi-Model Deliberation](https://docs.fastrouter.ai/explore-features/fastrouter-blend-multi-model-deliberation.md): Multi-model deliberation — ask a panel of models the same prompt in parallel, then have a judge model compare their answers into a structured analysis. - [Fallback Models](https://docs.fastrouter.ai/explore-features/fallback-models.md) - [Free Model Router (:free)](https://docs.fastrouter.ai/explore-features/free-model-router.md): FastRouter exposes select models at no charge via the :free slug — up to 10 requests per org per day, with no payment required for organizations having paid credit balance >$1. - [Flex Pricing](https://docs.fastrouter.ai/explore-features/flex-pricing.md): Access OpenAI and Google Gemini models at up to 50% lower cost by opting into flexible inference — ideal for background tasks, batch workloads, and latency-tolerant applications. - [Provider Routing Strategies](https://docs.fastrouter.ai/explore-features/provider-routing-strategies.md) - [Organization & Members](https://docs.fastrouter.ai/explore-features/organization-and-members.md): FastRouter supports role-based access control at the organization level to manage permissions and responsibilities effectively. - [Projects](https://docs.fastrouter.ai/explore-features/projects.md): Projects in FastRouter.ai provide a structure for specifying access and limits for keys used. - [Keys & Settings](https://docs.fastrouter.ai/explore-features/keys-and-settings.md): API keys in FastRouter allow granular control over access, usage, and budget. You can generate multiple keys with custom configurations for different users, projects, or integrations. - [Add External Keys (BYOK)](https://docs.fastrouter.ai/explore-features/add-external-keys-byok.md): Bring Your Own Key — Connect your own provider credentials to FastRouter and route traffic through your own accounts while retaining FastRouter's full routing, observability, and governance layer. - [Custom Evaluations](https://docs.fastrouter.ai/explore-features/custom-evaluations.md): FastRouter's Custom Evaluations lets you benchmark and compare AI models on your own data using LLM-based judges to automatically score accuracy, latency, and cost. - [Dataset Evaluations](https://docs.fastrouter.ai/explore-features/dataset-evaluations.md): FastRouter's Dataset Evaluations let you run a fixed set of test cases against one or more models and score every response with an LLM judge. - [Image Evaluations](https://docs.fastrouter.ai/explore-features/image-evaluations.md): FastRouter's Image Evaluations feature lets you assess the quality of AI-generated images at scale. - [Video Evaluations](https://docs.fastrouter.ai/explore-features/video-evaluations.md): Evaluate AI-generated videos at scale using LLM-based judges, with automated scoring across motion, sync, quality, and prompt adherence. - [Insights](https://docs.fastrouter.ai/explore-features/insights.md): Weekly, evidence-backed recommendations that reduce your LLM spend without giving up output quality. - [Prompt Library](https://docs.fastrouter.ai/explore-features/prompt-library.md): Manage, version, optimize, and deploy prompts independently of your code—enabling instant updates and rollbacks without application redeploys. - [Prompt Optimizations](https://docs.fastrouter.ai/explore-features/prompt-optimizations.md): Automatically refine your system prompts using GEPA — a reflective prompt evolution algorithm that iteratively improves prompts using LLM-judged feedback as gradients. - [Prompt Compression](https://docs.fastrouter.ai/explore-features/prompt-compression.md): Prompt Compression intelligently shrinks prompts before they're sent to an AI model, reducing token usage while maintaining response quality. It helps lower costs and maximize available context. - [Prompt Caching](https://docs.fastrouter.ai/explore-features/prompt-caching.md): FastRouter supports prompt caching on all major providers that offer it, with automatic sticky routing to maximize cache hits. - [Guardrails](https://docs.fastrouter.ai/explore-features/guardrails.md): Add deterministic and LLM-based guardrails to protect your AI applications from unwanted behaviors and ensure compliance. - [Batch Processing](https://docs.fastrouter.ai/explore-features/batch-processing.md): FastRouter supports batch processing for efficient handling of multiple API requests at scale. - [Image Processing](https://docs.fastrouter.ai/explore-features/image-processing.md): A guide to sending images via Base64 or URLs in API requests. - [PDF Processing](https://docs.fastrouter.ai/explore-features/pdf-processing.md): End-to-end guide to PDF ingestion in FastRouter chat completions, including plugin config, request examples, and billing details. - [Dynamic Tags Per Request](https://docs.fastrouter.ai/explore-features/dynamic-tags-per-request.md): Leverage dynamic tags for reporting, billing, or feature tracking with custom tags sent per request. - [Credits](https://docs.fastrouter.ai/explore-features/credits.md) - [Function Calling](https://docs.fastrouter.ai/explore-features/function-calling.md): FastRouter supports Function Calling for models capable of planning and invoking tools or functions. This allows LLMs to return structured function calls instead of natural language responses. - [Observability Destinations](https://docs.fastrouter.ai/explore-features/observability-destinations.md): Own your observability data. Stream request traces from FastRouter straight into your own Kafka cluster. - [Optimization Settings](https://docs.fastrouter.ai/explore-features/optimization-settings.md): Create reusable bundles of reasoning, flex tier and prompt compression, and apply them to virtual model aliases, evaluation runs and API keys. - [Provisioning Keys](https://docs.fastrouter.ai/explore-features/provisioning-keys.md): Provisioning Keys are special-purpose administrative tokens used to securely create, update, list, and delete Service Account Keys within your organization. - [Structured Outputs](https://docs.fastrouter.ai/explore-features/structured-outputs.md): FastRouter supports structured JSON outputs, allowing you to enforce a specific schema in LLM responses. This feature ensures that responses are machine-readable and conform to a predefined structure. - [Reasoning Tokens](https://docs.fastrouter.ai/explore-features/reasoning-tokens.md): FastRouter can return Reasoning Tokens (also known as thinking tokens) for supported models. - [Response Caching: Text](https://docs.fastrouter.ai/explore-features/response-caching.md): This page covers caching for text completions (POST /v1/chat/completions). For image and video generation, see Response Caching: Images & Video (Async). - [Response Caching: Images & Video (Async)](https://docs.fastrouter.ai/explore-features/response-caching-images-and-video-async.md): This page covers caching for asynchronous image generation (POST /api/v1/images/generations) and video generation (POST /api/v1/videos). For text completions, see Response Caching: Text. - [Realtime API (WebSocket)](https://docs.fastrouter.ai/explore-features/realtime-api-websocket.md): Enable real-time speech-to-speech and text conversations with AI models via WebSocket. - [Custom Alerts](https://docs.fastrouter.ai/explore-features/alerts.md): Alerts help you monitor your API usage and performance in real-time. Set up custom thresholds to get notified when metrics exceed expected values or change compared to historical baselines. - [System Alerts](https://docs.fastrouter.ai/explore-features/system-alerts.md): System alerts are automatic, pre-configured notifications that fire when your organization's credit balance or project/key budgets cross critical thresholds - [Tracing](https://docs.fastrouter.ai/explore-features/tracing.md): Group related LLM API calls into a single trace using a simple traceparent header. - [OpenAI Decisions & TypeSafe SystemOne](https://docs.fastrouter.ai/explore-features/openai-decisions-and-typesafe-systemone.md) - [OpenAI Decisions: GPT-6 Luna](https://docs.fastrouter.ai/explore-features/openai-decisions-and-typesafe-systemone/openai-decisions-gpt-6-luna.md): Get typed yes/no probabilities, choices, and rubric scores from OpenAI's gpt-6-luna through FastRouter's Decisions endpoint. - [TypeSafe SystemOne: Jev](https://docs.fastrouter.ai/explore-features/openai-decisions-and-typesafe-systemone/typesafe-systemone-jev.md): Evaluate text or structured data against typed yes/no, choice, and score questions using TypeSafe's Jev models through FastRouter. - [MCP Gateway](https://docs.fastrouter.ai/explore-features/mcp-gateway.md) - [Web Search](https://docs.fastrouter.ai/explore-features/web-search.md) - [Zero Data Retention](https://docs.fastrouter.ai/explore-features/zero-data-retention.md): FastRouter lets you restrict any request to Zero Data Retention (ZDR) providers by adding the :zdr suffix to the model slug. - [skill](https://docs.fastrouter.ai/skill.md): Use FastRouter's official skill.md file to give your AI coding assistants knowledge of FastRouter features - [Chat Completions](https://docs.fastrouter.ai/api-reference/chat-completions.md) - [Responses](https://docs.fastrouter.ai/api-reference/responses.md) - [Anthropic Messages Format](https://docs.fastrouter.ai/api-reference/anthropic-messages-format.md) - [Gemini Interactions API Format](https://docs.fastrouter.ai/api-reference/gemini-interactions-api-format.md) - [Gemini Native Format](https://docs.fastrouter.ai/api-reference/gemini-native-format.md): Note: The Gemini Interactions API Format is recommended for newer features and models via Gemini API. - [Embeddings](https://docs.fastrouter.ai/api-reference/embeddings.md) - [Image](https://docs.fastrouter.ai/api-reference/image.md) - [Image Generation](https://docs.fastrouter.ai/api-reference/image/image-generation.md) - [Image Edit](https://docs.fastrouter.ai/api-reference/image/image-edit.md) - [Audio](https://docs.fastrouter.ai/api-reference/audio.md) - [Text to Speech](https://docs.fastrouter.ai/api-reference/audio/text-to-speech.md) - [Speech to Text (Transcriptions)](https://docs.fastrouter.ai/api-reference/audio/transcriptions.md) - [Video](https://docs.fastrouter.ai/api-reference/video.md) - [Realtime](https://docs.fastrouter.ai/api-reference/realtime.md) - [Sessions](https://docs.fastrouter.ai/api-reference/sessions.md) - [Moderations](https://docs.fastrouter.ai/api-reference/moderations.md) - [List Models](https://docs.fastrouter.ai/api-reference/models.md) - [Models x Provider Breakdown](https://docs.fastrouter.ai/api-reference/models-x-provider-breakdown.md) - [List Providers](https://docs.fastrouter.ai/api-reference/list-providers.md) - [Provider x Model Supported Parameters](https://docs.fastrouter.ai/api-reference/provider-x-model-supported-parameters.md) - [Virtual Models](https://docs.fastrouter.ai/api-reference/virtual-models.md) - [Auto Router](https://docs.fastrouter.ai/api-reference/auto-router.md) - [Batch Processing](https://docs.fastrouter.ai/api-reference/batch-processing.md) - [Generations](https://docs.fastrouter.ai/api-reference/generations.md) - [Error Codes](https://docs.fastrouter.ai/api-reference/error-codes.md) - [Changelog](https://docs.fastrouter.ai/product-updates/changelog.md): New updates and improvements - [Coding Assistants](https://docs.fastrouter.ai/integrations/coding-assistants.md): Use FastRouter as an OpenAI-compatible provider inside your coding assistant. One key, 100+ models, full observability and cost control. - [Aider](https://docs.fastrouter.ai/integrations/coding-assistants/aider.md): Track usage, control costs, and add guardrails to your Aider coding sessions - [Claude Code](https://docs.fastrouter.ai/integrations/coding-assistants/claude-code.md): This guide walks you through setting up Claude Code to work with FastRouter.ai as your API provider. - [Codex CLI](https://docs.fastrouter.ai/integrations/coding-assistants/codex-cli.md): Integrating Codex CLI with FastRouter. - [Cursor](https://docs.fastrouter.ai/integrations/coding-assistants/cursor.md): Track usage, control costs, and add guardrails to your Cursor AI editor - [Cline](https://docs.fastrouter.ai/integrations/coding-assistants/cline.md): Track usage, control costs, and add guardrails to your Cline coding agent - [Roo Code](https://docs.fastrouter.ai/integrations/coding-assistants/roo-code.md): Track usage, control costs, and add guardrails to your Roo Code coding agent - [OpenCode](https://docs.fastrouter.ai/integrations/coding-assistants/opencode.md): Track usage, control costs, and add guardrails to your OpenCode coding agent - [DeepSeek Reasonix CLI](https://docs.fastrouter.ai/integrations/coding-assistants/deepseek-reasonix-cli.md): Integrating DeepSeek Reasonix CLI with FastRouter. - [Kilo Code](https://docs.fastrouter.ai/integrations/coding-assistants/kilo-code.md): Track usage, control costs, and add guardrails to your Kilo Code coding sessions - [DeepSeek Reasonix CLI](https://docs.fastrouter.ai/integrations/coding-assistants/deepseek-reasonix-cli-1.md): Route DeepSeek Reasonix CLI through FastRouter for unified model access, observability, failover, and organizational controls. - [XCode](https://docs.fastrouter.ai/integrations/coding-assistants/xcode.md): Track usage, control costs, and add guardrails to your Xcode AI coding sessions. - [Agents](https://docs.fastrouter.ai/integrations/agents.md): Route any Python agent framework through FastRouter. One key, 100+ models, and full cost visibility across every agent call. - [AutoGen](https://docs.fastrouter.ai/integrations/agents/autogen.md): Track usage, control costs, and add guardrails to your AutoGen multi-agent apps - [Agno](https://docs.fastrouter.ai/integrations/agents/agno.md): Track usage, control costs, and add guardrails to your Agno agents - [CrewAI](https://docs.fastrouter.ai/integrations/agents/crewai.md): Track usage, control costs, and add guardrails to your CrewAI multi-agent crews - [Langgraph](https://docs.fastrouter.ai/integrations/agents/langgraph.md): Track usage, control costs, and add guardrails to your LangGraph agents - [OpenAI Agent SDK](https://docs.fastrouter.ai/integrations/agents/openai-agent-sdk.md): Track usage, control costs, and add guardrails to your OpenAI Agents SDK applications - [OpenClaw](https://docs.fastrouter.ai/integrations/agents/openclaw.md) - [Running Hermes Agent with FastRouter](https://docs.fastrouter.ai/integrations/agents/running-hermes-agent-with-fastrouter.md) - [Pydantic AI](https://docs.fastrouter.ai/integrations/agents/pydantic-ai.md): Track usage, control costs, and add guardrails to your Pydantic AI agents - [App](https://docs.fastrouter.ai/integrations/app.md): Point ready-to-run agent apps and chat gateways at FastRouter. Install once, run a setup command, get 100+ models with full cost visibility. - [Instructor](https://docs.fastrouter.ai/integrations/app/instructor.md): Track usage, control costs, and add guardrails to your Instructor structured outputs - [LlamaIndex](https://docs.fastrouter.ai/integrations/app/llamaindex.md): Track usage, control costs, and add guardrails to your LlamaIndex applications - [LangChain](https://docs.fastrouter.ai/integrations/app/langchain.md): Track usage, control costs, and add guardrails to your LangChain applications - [n8n](https://docs.fastrouter.ai/integrations/app/n8n.md): Track usage, control costs, and add guardrails to your n8n AI workflows - [Open WebUI](https://docs.fastrouter.ai/integrations/app/open-webui.md): Track usage, control costs, and add guardrails to your Open WebUI deployment - [Scalekit](https://docs.fastrouter.ai/integrations/app/scalekit.md): Add per-user OAuth tool calling to your FastRouter agent with Scalekit. Gmail, GitHub, Slack, and more, with zero custom OAuth code. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation This site has an agentic ask interface you may use to query the documentation dynamically by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.fastrouter.ai/index.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.