OpenRouter

openrouter.ai

AI & Machine Learning

A unified interface for LLMs. Find the best models & prices for your prompts

llms.txt

OpenRouter | Documentation

Instructions for AI Agents

For clean Markdown of any page, append .md to the page URL
For a complete documentation index, see https://openrouter.ai/docs/llms.txt
For full documentation content in one file, see https://openrouter.ai/docs/llms-full.txt
For section-specific indexes, append /llms.txt to any section URL
For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://openrouter.ai/docs/_mcp/server

Docs

Quickstart: Get started with OpenRouter's unified API for hundreds of AI models. Learn how to integrate using the API directly, the Client SDKs, or the Agent SDK.
Principles: Learn about OpenRouter's guiding principles and mission. Understand our commitment to price optimization, standardized APIs, and high availability in AI model deployment.
Models: Access all major language models (LLMs) through OpenRouter's unified API. Browse available models, compare capabilities, and integrate with your preferred provider.
Multimodal Capabilities: Send images, PDFs, audio, and video to OpenRouter models, generate speech from text, or transcribe audio to text through our unified API.
Image Inputs: Send images to vision models through the OpenRouter API.
Image Generation: Generate images using AI models through the OpenRouter API.
PDF Inputs: Send PDF documents to any model on OpenRouter.
Audio: Send audio files to and receive audio responses from speech-capable models through the OpenRouter API.
Video Inputs: Send video files to video-capable models through the OpenRouter API.
Video Generation: Generate videos using AI models through the OpenRouter API.
Text-to-Speech: Generate speech audio from text using AI models through the OpenRouter API.
Speech-to-Text: Transcribe audio into text using AI models through the OpenRouter API. Access multiple STT providers with a single unified interface.
OAuth PKCE: Implement secure user authentication with OpenRouter using OAuth PKCE. Complete guide to setting up and managing OAuth authentication flows.
Management API Keys: Manage OpenRouter API keys programmatically through dedicated management endpoints. Create, read, update, and delete API keys for automated key distribution and control.
BYOK: Learn how to use your existing AI provider keys with OpenRouter. Integrate your own API keys while leveraging OpenRouter's unified interface and features.
Stripe Projects: Provision OpenRouter API access directly from the Stripe Projects CLI. Get an API key, manage credentials, and access 300+ AI models in seconds.
Frequently Asked Questions: Find answers to commonly asked questions about OpenRouter's unified API, model access, pricing, and integration.
Report Feedback: Learn how to report issues with AI generations on OpenRouter using the Report Feedback feature in the Chatroom and Activity page.
Model Fallbacks: Configure automatic failover between AI models when providers are down, rate-limited, or refuse requests.
Provider Routing: Route AI model requests across multiple providers intelligently. Learn how to optimize for cost, performance, and reliability with OpenRouter's provider routing.
Auto Exacto: Learn how Auto Exacto automatically optimizes provider ordering for tool-calling requests using throughput, success rate, and benchmark signals.
Private Models: Run your own custom, fine-tuned, or dedicated model deployments through the OpenRouter API. Private models are scoped to approved users and organizations and hidden from public model lists.
Free Variant: Access free models using the :free variant suffix.
Extended Variant: Access extended context window versions of models using the :extended variant.
Exacto Variant: Learn how to use the :exacto model variant to prioritize providers with stronger tool-calling quality signals.
Thinking Variant: Enable extended reasoning capabilities using the :thinking variant.
Online Variant: Enable real-time web search capabilities using the :online variant.
Nitro Variant: Access high-speed model inference using the :nitro variant.
Auto Router: Automatically select the best AI model for your prompts using OpenRouter's Auto Router powered by NotDiamond.
Body Builder: Use natural language to generate multiple OpenRouter API requests for parallel model execution.
Free Models Router: Route requests to free AI models automatically using OpenRouter's Free Models Router.
Latest Model Resolution: Use ~author/family-latest slugs to automatically route to the newest model in a family on OpenRouter.
Pareto Router: Route coding requests by a single minimum coding score using OpenRouter's Pareto Router.
Fusion Router: Use the openrouter/fusion model slug to access multi-model deliberation — a panel of models, a judge, and a final answer — in a single API call.
Workspaces: Separate your OpenRouter projects into independent environments, each with its own API keys, routing defaults, guardrails, and observability.
Presets: Learn how to use OpenRouter's presets to manage model configurations, system prompts, and parameters across your applications.
Response Caching: Cache identical LLM requests with OpenRouter's response caching feature. Reduce costs and latency for agent workflows, unit testing, and repeated context processing.
Tool & Function Calling: Use tools (or functions) in your prompts with OpenRouter. Learn how to use tools with OpenAI, Anthropic, and other models that support tool calling.
Server Tools: Add powerful server-side tools like web search, web fetch, datetime, and image generation to any model on OpenRouter. Models decide when to call them — OpenRouter executes them automatically.
Web Search: Add real-time web search to any model on OpenRouter. The model decides when to search, OpenRouter executes it, and results are returned with citations.
Web Fetch: Add URL content fetching to any model on OpenRouter. The model decides when to fetch, OpenRouter retrieves the content, and results are returned as text.
Datetime: Add current date and time awareness to any model on OpenRouter. The model calls the tool when it needs temporal context.
Image Generation: Add AI image generation to any model on OpenRouter. The model calls the tool with a prompt, OpenRouter generates the image and returns it.
Apply Patch: Enable any model on OpenRouter to propose file edits using V4A diff patches. The model generates the patch, OpenRouter validates it, and your application applies it.
Fusion: Let any model invoke an expert panel and judge to surface consensus, contradictions, coverage gaps, unique insights, and blind spots.
Advisor: Let a fast executor model consult a higher-intelligence advisor model for guidance mid-generation, with any OpenRouter model and optional sub-agent tools.
Plugins: Enable powerful plugins like web search, PDF processing, and response healing to extend any model's capabilities on OpenRouter.
Web Search: Enable real-time web search capabilities in your AI model responses. Add factual, up-to-date information to any model's output with OpenRouter's web search feature.
Response Healing: Automatically validate and repair malformed JSON responses from AI models. Ensure your responses match your schema even when models return imperfect formatting.
Fusion: Get richer answers by running a panel of models in parallel and comparing their responses through a judge. Fusion makes this a one-line addition to any OpenRouter request.
Structured Outputs: Enforce JSON Schema validation on AI model responses. Get consistent, type-safe outputs and avoid parsing errors with OpenRouter's structured output feature.
Message Transforms: Transform and optimize messages before sending them to AI models. Learn about middle-out compression and context window optimization with OpenRouter.
Zero Completion Insurance: Learn how OpenRouter protects users from being charged for failed or empty AI responses with zero completion insurance.
Zero Data Retention: Learn how OpenRouter gives you control over your data
App Attribution: Learn how to attribute your API usage to your app and appear in OpenRouter's app rankings and model analytics.
Guardrails: Set spending limits, restrict model access, and enforce data policies for your organization members and API keys with OpenRouter guardrails.
Prompt Injection Detection: Reference documentation for the regex-based prompt injection detection patterns used by OpenRouter guardrails, inspired by the OWASP LLM Prompt Injection Prevention Cheat Sheet.
Sensitive Info Guardrail: Protect sensitive data in your AI requests with OpenRouter Sensitive Info Guardrails. Automatically detect and redact or block PII like emails, phone numbers, names, addresses, and more.
Service Tiers: Learn how to use service tiers on OpenRouter to control cost and latency tradeoffs when routing requests to AI providers.
Sovereign AI: Learn how OpenRouter enables sovereign AI with in-region routing, data residency controls, and compliance features that keep your AI workloads within national and regional boundaries.
Router Metadata: Opt in to OpenRouter routing metadata to see which provider was selected, fallback attempts, and pipeline stages applied to your request.
Input & Output Logging: Store your prompts and completions privately on OpenRouter for debugging, evaluation, and optimization. View them in your Logs page.
Broadcast: Connect your LLM observability platforms to automatically receive traces from your OpenRouter requests. Supports Langfuse, Datadog, Braintrust, and more.
Arize AI: Connect Arize AI to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for Arize integration.
Braintrust: Connect Braintrust to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for Braintrust integration.
ClickHouse: Connect ClickHouse to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for ClickHouse integration.
Comet Opik: Connect Comet Opik to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for Opik integration.
Datadog: Connect Datadog LLM Observability to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for Datadog integration.
Grafana Cloud: Connect Grafana Cloud to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for Grafana Cloud integration.
Langfuse: Connect Langfuse to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for Langfuse integration.
LangSmith: Connect LangSmith to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for LangSmith integration.
New Relic: Connect New Relic to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for New Relic integration.
OpenTelemetry Collector: Connect any OpenTelemetry-compatible backend to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for OTLP integration.
PostHog: Connect PostHog to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for PostHog integration.
Ramp: Connect Ramp to automatically receive AI usage traces from your OpenRouter requests. Step-by-step setup guide for Ramp integration.
S3 / S3-Compatible: Connect Amazon S3 or S3-compatible storage to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for S3 integration.
Sentry: Connect Sentry to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for Sentry integration.
Snowflake: Connect Snowflake to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for Snowflake integration.
W&B Weave: Connect W&B Weave to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for W&B Weave integration.
Webhook: Connect any HTTP endpoint to automatically receive traces from your OpenRouter requests. Step-by-step setup guide for Webhook integration.
Data Collection: Learn what data OpenRouter collects and how it's used.
Provider Logging: Understand how AI providers handle logging and data retention when you use OpenRouter.
Latency and Performance: Learn about OpenRouter's performance characteristics, latency optimizations, and best practices for achieving optimal response times.
Prompt Caching: Reduce your AI model costs with OpenRouter's prompt caching feature. Learn how to cache and reuse responses across OpenAI, Anthropic Claude, and DeepSeek models.
Uptime Optimization: Learn how OpenRouter maximizes AI model uptime through real-time monitoring, intelligent routing, and automatic fallbacks across multiple providers.
Reasoning Tokens: Learn how to use reasoning tokens to enhance AI model outputs. Implement step-by-step reasoning traces for better decision making and transparency.
Provider Integration: Learn how to integrate your AI models with OpenRouter. Complete guide for providers to make their models available through OpenRouter's unified API.
Frameworks and Integrations Overview: Integrate OpenRouter using popular frameworks and SDKs. Complete guides for OpenAI SDK, LangChain, PydanticAI, and Vercel AI SDK integration.
Awesome OpenRouter: Discover community-built projects and apps powered by OpenRouter. Submit your own project to the awesome-openrouter list.
Effect AI SDK: Integrate OpenRouter using the Effect AI SDK. Complete guide for integrating the Effect AI SDK with OpenRouter.
Arize: Integrate OpenRouter using Arize for observability and tracing. Complete guide for Arize integration with OpenRouter for Python and JavaScript applications.
LangChain: Integrate OpenRouter using LangChain framework. Complete guide for LangChain integration with OpenRouter for Python and JavaScript.
LiveKit: Integrate OpenRouter using LiveKit Agents framework. Complete guide for LiveKit integration with OpenRouter to build voice AI agents with access to 300+ models.
Langfuse: Integrate OpenRouter using Langfuse for observability and tracing. Complete guide for Langfuse integration with OpenRouter for Python applications.
Mastra: Integrate OpenRouter using Mastra framework. Complete guide for Mastra integration with OpenRouter for unified AI model access.
OpenAI SDK: Integrate OpenRouter using the official OpenAI SDK. Complete guide for OpenAI SDK integration with OpenRouter for Python and TypeScript.
Anthropic Agent SDK: Integrate OpenRouter using the Anthropic Agent SDK. Complete guide for building AI agents with OpenRouter in Python and TypeScript.
PydanticAI: Integrate OpenRouter using PydanticAI framework. Complete guide for PydanticAI integration with OpenRouter for Python applications.
Replit: Add your OpenRouter API key to Replit to access 300+ AI models in Replit Agent and your Replit apps. Covers BYOK setup and project Secrets.
TanStack AI: Integrate OpenRouter using TanStack AI. Complete guide for TanStack AI integration with OpenRouter for React, Solid, and Preact applications.
Vercel AI SDK: Integrate OpenRouter using Vercel AI SDK. Complete guide for Vercel AI SDK integration with OpenRouter for Next.js applications.
Xcode: Integrate OpenRouter with Apple Intelligence in Xcode 26. Complete setup guide for accessing hundreds of AI models directly in your Xcode development environment.
Zapier: Build powerful AI automations by connecting OpenRouter with 8000+ apps through Zapier. Access 300+ AI models in your workflows.
Infisical: Set up automatic API key rotation for OpenRouter using Infisical. Complete guide for secure key management and zero-downtime rotation.
API Reference: Comprehensive guide to OpenRouter's API. Learn about request/response schemas, authentication, parameters, and integration with multiple AI model providers.
Streaming: Learn how to implement streaming responses with OpenRouter's API. Complete guide to Server-Sent Events (SSE) and real-time model outputs.
Embeddings: Generate vector embeddings from text and images using OpenRouter's unified embeddings API. Access multiple embedding models from different providers with a single interface.
Limits: Learn about OpenRouter's API rate limits, credit-based quotas, and DDoS protection. Configure and monitor your model usage limits effectively.
Authentication: Learn how to authenticate with OpenRouter using API keys and Bearer tokens. Complete guide to secure authentication methods and best practices.
Parameters: Learn about all available parameters for OpenRouter API requests. Configure temperature, max tokens, top_p, and other model-specific settings.
Errors and Debugging: Learn how to handle errors and debug requests in OpenRouter API interactions. Comprehensive guide to error codes, messages, debugging options, and best practices.
Responses API Beta: Beta version of OpenRouter's OpenAI-compatible Responses API. Stateless transformation layer with support for reasoning, tool calling, and web search.
Basic Usage: Learn the basics of OpenRouter's Responses API Beta with simple text input examples and response handling.
Reasoning: Access advanced reasoning capabilities with configurable effort levels and encrypted reasoning chains using OpenRouter's Responses API Beta.
Tool Calling: Integrate function calling with support for parallel execution and complex tool interactions using OpenRouter's Responses API Beta.
Web Search: Enable web search capabilities with real-time information retrieval and citation annotations using OpenRouter's Responses API Beta.
Error Handling: Learn how to handle errors in OpenRouter's Responses API Beta with the basic error response format.
Client SDKs: Lightweight, type-safe SDK clients for calling AI models through OpenRouter. Available for TypeScript, Python, and Go.
Usage for Agents: Add OpenRouter Client SDKs skills to AI coding assistants like Claude Code, Cursor, GitHub Copilot, and more. Enable your AI to code with the OpenRouter Client SDKs.
TypeScript SDK: Complete guide to using the OpenRouter TypeScript SDK. Learn how to integrate AI models into your TypeScript applications.
Analytics - TypeScript SDK: Analytics method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
APIKeys - TypeScript SDK: APIKeys method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Byok - TypeScript SDK: Byok method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Chat - TypeScript SDK: Chat method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Credits - TypeScript SDK: Credits method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Datasets - TypeScript SDK: Datasets method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Embeddings - TypeScript SDK: Embeddings method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Endpoints - TypeScript SDK: Endpoints method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Generations - TypeScript SDK: Generations method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Guardrails - TypeScript SDK: Guardrails method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Models - TypeScript SDK: Models method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
OAuth - TypeScript SDK: OAuth method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Observability - TypeScript SDK: Observability method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Organization - TypeScript SDK: Organization method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Presets - TypeScript SDK: Presets method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Providers - TypeScript SDK: Providers method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Rerank - TypeScript SDK: Rerank method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Beta.Responses - TypeScript SDK: Beta.Responses method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Transcriptions - TypeScript SDK: Transcriptions method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Speech - TypeScript SDK: Speech method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
VideoGeneration - TypeScript SDK: VideoGeneration method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Workspaces - TypeScript SDK: Workspaces method documentation for the OpenRouter TypeScript SDK. Learn how to use this API endpoint with code examples.
Python SDK: Complete guide to using the OpenRouter Python SDK. Learn how to integrate AI models into your Python applications.
Analytics - Python SDK: Analytics method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
APIKeys - Python SDK: APIKeys method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Byok - Python SDK: Byok method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Chat - Python SDK: Chat method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Credits - Python SDK: Credits method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Datasets - Python SDK: Datasets method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Embeddings - Python SDK: Embeddings method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Endpoints - Python SDK: Endpoints method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Generations - Python SDK: Generations method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Guardrails - Python SDK: Guardrails method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Models - Python SDK: Models method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
OAuth - Python SDK: OAuth method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Observability - Python SDK: Observability method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Organization - Python SDK: Organization method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Presets - Python SDK: Presets method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Providers - Python SDK: Providers method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Rerank - Python SDK: Rerank method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Beta.Responses - Python SDK: Beta.Responses method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Transcriptions - Python SDK: Transcriptions method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Speech - Python SDK: Speech method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
VideoGeneration - Python SDK: VideoGeneration method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Workspaces - Python SDK: Workspaces method documentation for the OpenRouter Python SDK. Learn how to use this API endpoint with code examples.
Analytics - Go SDK: Analytics method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
APIKeys - Go SDK: APIKeys method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Byok - Go SDK: Byok method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Chat - Go SDK: Chat method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Credits - Go SDK: Credits method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Datasets - Go SDK: Datasets method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Embeddings - Go SDK: Embeddings method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Endpoints - Go SDK: Endpoints method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Generations - Go SDK: Generations method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Guardrails - Go SDK: Guardrails method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Models - Go SDK: Models method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
OAuth - Go SDK: OAuth method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Observability - Go SDK: Observability method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Organization - Go SDK: Organization method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Presets - Go SDK: Presets method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Providers - Go SDK: Providers method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Rerank - Go SDK: Rerank method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Beta.Responses - Go SDK: Beta.Responses method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Transcriptions - Go SDK: Transcriptions method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Speech - Go SDK: Speech method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
VideoGeneration - Go SDK: VideoGeneration method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
Workspaces - Go SDK: Workspaces method documentation for the OpenRouter Go SDK. Learn how to use this API endpoint with code examples.
DevTools: Comprehensive development tools for the OpenRouter SDK. Capture telemetry, visualize requests, and debug your AI applications with ease.
Migrating to @openrouter/agent: Step-by-step guide to migrating agent toolkit code from @openrouter/sdk to the new @openrouter/agent package.
Agent SDK: Build AI agents on OpenRouter with callModel, tool definitions, stop conditions, and automatic conversation state management.
Usage for Agents: Add OpenRouter Agent SDK skills to AI coding assistants like Claude Code, Cursor, GitHub Copilot, and more. Enable your AI to code with the OpenRouter Agent SDK.
Call Model (Typescript): Learn how to use callModel for text generation, streaming, and tool calling with automatic execution. Access 300+ LLMs through a single API.
Working with Items: Learn the items-based streaming paradigm for callModel. Replace items by ID instead of accumulating chunks for simpler React state management.
API Reference: Complete API reference for callModel, ModelResult, tool types, and helper functions in the OpenRouter SDK.
Dynamic Parameters: Use async functions to dynamically compute callModel parameters. Adapt model selection, temperature, and instructions based on conversation state.
Next Turn Params: Build encapsulated, context-aware tools with nextTurnParams. Create skills systems, plugins, and adaptive multi-turn agents.
Stop Conditions: Control multi-turn execution with stopWhen. Use built-in helpers or custom conditions to stop by step count, tool calls, cost, or tokens.
Streaming: Learn to stream LLM responses with callModel. Covers text streaming, reasoning streams, message updates, and concurrent consumers.
Text Generation: Learn how to generate text with callModel. Covers input formats, model selection, system instructions, and response handling.
Message Formats: Convert between OpenAI chat format, Anthropic Claude format, and OpenResponses format. Easy migration from other SDKs.
Tools: Create strongly-typed tools for LLMs with Zod schemas. Learn about regular tools, generator tools with progress, manual tools, human-in-the-loop tools, and automatic multi-turn execution.
Tool Approval & State Persistence: Add human-in-the-loop approval for sensitive tool calls and persist conversation state across callModel runs. Supports approval gates, resumption, and interruption recovery.
Weather Tool: Build a weather tool with external API integration, Zod validation, error handling, and environment configuration.
Skills Loader: Build a complete skills system like Claude Code using nextTurnParams for context injection, idempotency, and multi-skill loading.
Quickstart: Build a Chat App: Build a working chat app in TypeScript that streams responses from any model on OpenRouter. Install the SDK, send a message, and handle multi-turn conversations.
Enterprise Quickstart: A comprehensive guide for enterprise customers to get started with OpenRouter. Learn about organizations, workspaces, API key management, security controls, and observability.
Free Models Router: Learn how to use the Free Models Router in the OpenRouter Chat Playground for zero-cost inference.
Automatic Code Review: Set up automatic, non-blocking code reviews for Claude Code. A stop hook triggers a background reviewer agent via OpenRouter — observable, customizable, and cost-monitored.
Claude Code: Learn how to use Claude Code with OpenRouter for improved reliability, provider failover, and organizational controls.
Claude Desktop: Learn how to use Claude Desktop with OpenRouter through built-in third-party inference mode.
Codex CLI: Learn how to configure Codex CLI to use OpenRouter for agentic coding with the latest GPT models and more.
Hermes Agent: Learn how to configure Hermes Agent to use OpenRouter for AI-powered coding, automation, and multi-platform messaging.
Junie CLI: Integrate OpenRouter with JetBrains Junie CLI. Complete setup guide for using hundreds of AI models with the Junie agentic coding tool.
Using MCP Servers with OpenRouter: Learn how to use MCP Servers with OpenRouter
OpenClaw 🦞: Learn how to configure OpenClaw to use OpenRouter for AI agents across multiple messaging platforms.
OpenCode: Learn how to configure OpenCode to use OpenRouter for agentic coding with access to hundreds of AI models.
Add Human-in-the-Loop Controls to an Agent SDK Agent: Add HITL controls to an existing OpenRouter Agent SDK agent so routine tool calls resolve automatically and high-stakes decisions pause for human review.
Build a Long-Horizon Agent: Run agents for hours, not seconds. Cap cost and step count, persist state for resumability, stream progress, and drive the same loop from voice input.
Build Your Own Agent TUI: Use the create-agent-tui skill to scaffold a custom AI agent in TypeScript with a customizable terminal UI, configurable tools, and streaming via @openrouter/agent.
Build Your Own Headless Agent: Use the create-headless-agent skill to scaffold a headless AI agent in TypeScript + Bun with configurable tools, output modes, and streaming via @openrouter/agent.
Choose a Video Generation Model: Fetch OpenRouter video model metadata, filter by capability, and score models by speed, cost, and quality priorities before submitting a video job.
Generate and Download a Video from Text: Submit an OpenRouter text-to-video generation job, poll the job status, and download the finished video file.
Get Video Results with Webhooks: Receive OpenRouter video job results through webhooks, preserve the raw request body, and verify the webhook signature.
Guide a Video with Reference Images: Submit an OpenRouter reference-to-video job with input_references when images should guide the generated result.
Turn an Image into a Video: Submit an OpenRouter image-to-video job with frame_images, poll for completion, and download the finished clip.
Use Provider-Specific Video Options: Use allowed_passthrough_parameters and provider.options to send model-specific video generation controls through OpenRouter.
Distillation: Learn how to use the distillable filter to ensure compliance with provider and model creator policies when using model outputs for training or distillation.
Claude 4.7 Migration Guide: Learn about the breaking changes in Claude 4.7 Opus — removed sampling parameters, adaptive-only thinking, and the new xhigh effort level.
Claude 4.6 Migration Guide: Learn about adaptive thinking and the new max effort level in Claude 4.6.
GPT-5.4 Migration Guide: Learn how to use the phase field for GPT-5.3 Codex, GPT-5.4, and GPT-5.4 Pro on OpenRouter.
RAG with Embeddings & Rerank: Learn how to build RAG pipelines using OpenRouter embeddings for retrieval and rerank models for precision, then generate answers with LLMs — all through a single API.
Red Teaming: Understand OpenRouter policies on red teaming, jailbreaking, and adversarial model testing. Learn how to get approval for legitimate security research.
Activity Export: Learn how to export your OpenRouter usage data as CSV or PDF reports, grouped by API key, model, or organization member.
API Key Rotation: Learn how to securely rotate your OpenRouter API keys using the key minting API. Includes best practices and BYOK advantages for simplified key management.
Crypto API: Coinbase deprecated the APIs used by the legacy Coinbase Commerce crypto credits endpoint, which now returns 410 Gone.
Organization Management: Learn how to create and manage organizations on OpenRouter for team collaboration, shared credits, and centralized API management.
Usage Accounting: Learn how to track AI model usage including prompt tokens, completion tokens, and cached tokens without additional API calls.
User Tracking: Learn how to use the user parameter to track your own user IDs with OpenRouter. Get detailed reporting and analytics on your sub-users.