# OpenRouter

> A unified API for every major LLM. One endpoint, hundreds of models, with
> routing, fallbacks, and cost tracking across providers.

`/{author}/{model}/llms.txt` returns one machine-readable guide with sections for every confirmed
OpenRouter API that serves a public model: text/chat, image, video, speech-to-text, and
text-to-speech.

## Ori

- [Ori Eval](https://openrouter.ai/ori/eval.md): Find the best model for your project — run your agent on your own prompts, on a harness and model that stay pinned, and rank the candidates.
- [spawn-ori-eval skill](https://openrouter.ai/skills/spawn-ori-eval): For coding agents. Read it to run a model eval by handing it to Ori, so the eval is authored and graded on a pinned harness and model rather than one you improvised.
- [install-ori-harness skill](https://openrouter.ai/skills/install-ori-harness): For coding agents. Read it to install Ori, sign in, run an existing agent CLI through Ori, choose an OpenRouter model, and verify the setup.
- [Install Ori](https://openrouter.ai/labs/ori/install.sh): `curl -fsSL https://openrouter.ai/labs/ori/install.sh | bash`
- [Ori Eval docs](https://openrouter.ai/docs/guides/ori/eval.md): Writing `*.eval.ts` files, LLM-as-judge grading, and model bakeoffs.

## Skills

- [Skills](https://github.com/OpenRouterTeam/skills): Every skill OpenRouter publishes. Each one is served as raw markdown from `https://openrouter.ai/skills/<name>` (also at `/.well-known/skills/<name>/SKILL.md`, for agents that look there first).
- [Agent guide](https://openrouter.ai/agents.md): Using OpenRouter from a coding agent.

## Benchmarks

- [Benchmarks](https://openrouter.ai/benchmarks): Browse live independent benchmark results for OpenRouter models, providers, and search engines.
- [GET /api/v1/benchmarks](https://openrouter.ai/api/v1/benchmarks): Fetch benchmark results programmatically with a valid OpenRouter API key.
- [Benchmarks API reference](https://openrouter.ai/docs/api/api-reference/benchmarks/list-benchmarks): Read the API contract for listing benchmark results and supported filters.

## Docs

- [Quickstart](https://openrouter.ai/docs/quickstart.md): Get started with OpenRouter
- [Batch API Quickstart](https://openrouter.ai/docs/batch-quickstart.md): Submit and retrieve asynchronous batches of inference requests
- [Principles](https://openrouter.ai/docs/guides/overview/principles.md): Core principles and values of OpenRouter
- [Models](https://openrouter.ai/docs/guides/overview/models.md): One API for hundreds of models
- [MCP](https://openrouter.ai/docs/guides/overview/mcp-server.md): Connect your AI coding tools to OpenRouter over MCP
- [Multimodal Capabilities](https://openrouter.ai/docs/guides/overview/multimodal/overview.md): Send images, PDFs, audio, and video to OpenRouter models, generate speech from text, or transcribe audio to text
- [Image Generation](https://openrouter.ai/docs/guides/overview/multimodal/image-generation.md): How to generate images with OpenRouter's dedicated Image API
- [Video Generation](https://openrouter.ai/docs/guides/overview/multimodal/video-generation.md): How to generate videos with OpenRouter models
- [Text-to-Speech](https://openrouter.ai/docs/guides/overview/multimodal/tts.md): How to generate speech audio from text with OpenRouter models
- [Speech-to-Text](https://openrouter.ai/docs/guides/overview/multimodal/stt.md): How to transcribe audio into text with OpenRouter models
- [Audio](https://openrouter.ai/docs/guides/overview/multimodal/audio.md): How to send and receive audio with OpenRouter models
- [PDF Inputs](https://openrouter.ai/docs/guides/overview/multimodal/pdfs.md): How to send PDFs to OpenRouter models
- [Image Inputs](https://openrouter.ai/docs/guides/overview/multimodal/image-understanding.md): How to send images to OpenRouter models
- [Video Inputs](https://openrouter.ai/docs/guides/overview/multimodal/videos.md): How to send video files to OpenRouter models
- [OAuth PKCE](https://openrouter.ai/docs/guides/overview/auth/oauth.md): Connect your users to OpenRouter
- [Management API Keys](https://openrouter.ai/docs/guides/overview/auth/management-api-keys.md): Manage API keys programmatically
- [BYOK](https://openrouter.ai/docs/guides/overview/auth/byok.md): Bring your own provider API keys
- [Stripe Projects](https://openrouter.ai/docs/guides/overview/stripe-projects.md): Add OpenRouter to your app with the Stripe Projects CLI
- [Frequently Asked Questions](https://openrouter.ai/docs/faq.md): Common questions about OpenRouter
- [Report Feedback](https://openrouter.ai/docs/guides/overview/report-feedback.md)
- [Model Fallbacks](https://openrouter.ai/docs/guides/routing/model-fallbacks.md): Automatic failover between models
- [Provider Routing](https://openrouter.ai/docs/guides/routing/provider-selection.md): Route requests to the best provider
- [Auto Exacto](https://openrouter.ai/docs/guides/routing/auto-exacto.md): Automatic tool-calling provider optimization
- [Private Models](https://openrouter.ai/docs/guides/routing/private-models.md): Bring your own model to OpenRouter, scoped to approved users and organizations
- [Free Variant](https://openrouter.ai/docs/guides/routing/model-variants/free.md): Access free models with the :free variant
- [Extended Variant](https://openrouter.ai/docs/guides/routing/model-variants/extended.md): Extended context windows with :extended
- [Exacto Variant](https://openrouter.ai/docs/guides/routing/model-variants/exacto.md): Route requests with quality-first provider sorting
- [Thinking Variant](https://openrouter.ai/docs/guides/routing/model-variants/thinking.md): Enable extended reasoning with :thinking
- [Online Variant](https://openrouter.ai/docs/guides/routing/model-variants/online.md): Real-time web search with :online
- [Nitro Variant](https://openrouter.ai/docs/guides/routing/model-variants/nitro.md): High-speed model inference with :nitro
- [Floor Variant](https://openrouter.ai/docs/guides/routing/model-variants/floor.md): Lowest-cost model inference with :floor
- [Auto Router](https://openrouter.ai/docs/guides/routing/routers/auto-router.md): Automatically select the best model for your prompt
- [Body Builder](https://openrouter.ai/docs/guides/routing/routers/body-builder.md): Generate multiple parallel API requests from natural language
- [Free Models Router](https://openrouter.ai/docs/guides/routing/routers/free-router.md): Get free AI inference by routing to available free models
- [Latest Model Resolution](https://openrouter.ai/docs/guides/routing/routers/latest-resolution.md): Always target the newest version of a model family with a single slug
- [Pareto Router](https://openrouter.ai/docs/guides/routing/routers/pareto-router.md): Pick a coding model by minimum coding score without choosing a specific model
- [Fusion Router](https://openrouter.ai/docs/guides/routing/routers/fusion-router.md): Multi-model deliberation as a model slug
- [Workspaces](https://openrouter.ai/docs/guides/features/workspaces.md): Organize your projects, teams, and agents into separate environments
- [Workspace Budgets](https://openrouter.ai/docs/guides/features/workspaces/workspace-budgets.md): Set spending limits per workspace with automatic enforcement
- [Switching Workspaces](https://openrouter.ai/docs/guides/features/workspaces/switching.md): Change which workspace your Chat and Fusion requests run in.
- [Single Sign-On (SSO)](https://openrouter.ai/docs/guides/features/sso.md): Let your team sign in to OpenRouter through your identity provider
- [SCIM Group Mappings](https://openrouter.ai/docs/guides/features/scim-mappings.md): Automatically provision workspace access from your identity provider groups
- [Presets](https://openrouter.ai/docs/guides/features/presets.md): Manage your LLM configurations
- [Custom Classifiers](https://openrouter.ai/docs/guides/features/classifiers.md): Automatically categorize LLM generations in your workspace
- [Response Caching](https://openrouter.ai/docs/guides/features/response-caching.md): Cache responses for identical API requests to save time and money
- [Tool & Function Calling](https://openrouter.ai/docs/guides/features/tool-calling.md): Use tools in your prompts
- [Server Tools](https://openrouter.ai/docs/guides/features/server-tools.md): Tools operated by OpenRouter that models can call during request
- [Web Search](https://openrouter.ai/docs/guides/features/server-tools/web-search.md): Give any model access to real-time web information
- [Web Fetch](https://openrouter.ai/docs/guides/features/server-tools/web-fetch.md): Give any model the ability to fetch content from URLs
- [Datetime](https://openrouter.ai/docs/guides/features/server-tools/datetime.md): Give any model access to the current date and time
- [Image Generation](https://openrouter.ai/docs/guides/features/server-tools/image-generation.md): Generate images from text prompts with any model
- [Apply Patch](https://openrouter.ai/docs/guides/features/server-tools/apply-patch.md): Let models propose file changes via V4A diffs
- [Shell](https://openrouter.ai/docs/guides/features/server-tools/shell.md): Give any model a sandboxed hosted shell on the Responses and Messages APIs
- [Search Models](https://openrouter.ai/docs/guides/features/server-tools/search-models.md): Let any model search the OpenRouter model catalog
- [Fusion](https://openrouter.ai/docs/guides/features/server-tools/fusion.md): Multi-model deliberation as a server tool
- [Advisor](https://openrouter.ai/docs/guides/features/server-tools/advisor.md): Consult a stronger model mid-generation as a server tool
- [Subagent](https://openrouter.ai/docs/guides/features/server-tools/subagent.md): Delegate tasks to a smaller, faster model as a server tool
- [Plugins](https://openrouter.ai/docs/guides/features/plugins.md): Extend model capabilities with OpenRouter plugins
- [Web Search](https://openrouter.ai/docs/guides/features/plugins/web-search.md): Model-agnostic grounding
- [Response Healing](https://openrouter.ai/docs/guides/features/plugins/response-healing.md): Automatically fix malformed JSON responses
- [Fusion](https://openrouter.ai/docs/guides/features/plugins/fusion.md): Multi-model analysis with an analyst model
- [Structured Outputs](https://openrouter.ai/docs/guides/features/structured-outputs.md): Return structured data from your models
- [Message Transforms](https://openrouter.ai/docs/guides/features/message-transforms.md): Transform prompt messages
- [Zero Completion Insurance](https://openrouter.ai/docs/guides/features/zero-completion-insurance.md): OpenRouter will not charge you for zero token responses
- [Zero Data Retention](https://openrouter.ai/docs/guides/features/zdr.md): How OpenRouter gives you control over your data
- [App Attribution](https://openrouter.ai/docs/app-attribution.md): Get your app featured in OpenRouter rankings and analytics
- [Guardrails](https://openrouter.ai/docs/guides/features/guardrails.md): Control spending and model access for your organization
- [Prompt Injection Detection](https://openrouter.ai/docs/guides/features/guardrails/prompt-injection.md): Regex-based prompt injection guardrail patterns
- [Allowlist](https://openrouter.ai/docs/guides/features/guardrails/prompt-injection/allowlist.md): Exclude known-safe phrases from prompt injection detection
- [Sensitive Info Guardrail](https://openrouter.ai/docs/guides/features/guardrails/sensitive-info.md): Automatically detect and handle sensitive information in API requests
- [Service Tiers](https://openrouter.ai/docs/guides/features/service-tiers.md): Control cost and latency tradeoffs with service tier selection
- [Sovereign AI](https://openrouter.ai/docs/guides/features/sovereign-ai.md): Keep AI workloads within national and regional boundaries
- [Router Metadata](https://openrouter.ai/docs/guides/features/router-metadata.md): Surface routing decisions on every response with a single opt-in header
- [Input & Output Logging](https://openrouter.ai/docs/guides/features/input-output-logging.md): Privately store and review your prompts and completions
- [Broadcast](https://openrouter.ai/docs/guides/features/broadcast.md): Send traces to external observability platforms
- [Arize AX](https://openrouter.ai/docs/guides/features/broadcast/arize.md): Send traces to Arize AX
- [Braintrust](https://openrouter.ai/docs/guides/features/broadcast/braintrust.md): Send traces to Braintrust
- [ClickHouse](https://openrouter.ai/docs/guides/features/broadcast/clickhouse.md): Send traces to ClickHouse
- [Comet Opik](https://openrouter.ai/docs/guides/features/broadcast/opik.md): Send traces to Comet Opik
- [Datadog](https://openrouter.ai/docs/guides/features/broadcast/datadog.md): Send traces to Datadog
- [Google BigQuery](https://openrouter.ai/docs/guides/features/broadcast/bigquery.md): Send traces to Google BigQuery
- [Grafana Cloud](https://openrouter.ai/docs/guides/features/broadcast/grafana.md): Send traces to Grafana Cloud
- [Langfuse](https://openrouter.ai/docs/guides/features/broadcast/langfuse.md): Send traces to Langfuse
- [LangSmith](https://openrouter.ai/docs/guides/features/broadcast/langsmith.md): Send traces to LangSmith
- [New Relic](https://openrouter.ai/docs/guides/features/broadcast/newrelic.md): Send traces to New Relic
- [OpenTelemetry Collector](https://openrouter.ai/docs/guides/features/broadcast/otel-collector.md): Send traces to any OpenTelemetry-compatible backend
- [PostHog](https://openrouter.ai/docs/guides/features/broadcast/posthog.md): Send traces to PostHog
- [Raindrop](https://openrouter.ai/docs/guides/features/broadcast/raindrop.md): Send traces to Raindrop
- [Ramp](https://openrouter.ai/docs/guides/features/broadcast/ramp.md): Send traces to Ramp
- [S3 / S3-Compatible](https://openrouter.ai/docs/guides/features/broadcast/s3.md): Send traces to Amazon S3 or S3-compatible storage
- [Sentry](https://openrouter.ai/docs/guides/features/broadcast/sentry.md): Send traces to Sentry
- [Snowflake](https://openrouter.ai/docs/guides/features/broadcast/snowflake.md): Send traces to Snowflake
- [W&B Weave](https://openrouter.ai/docs/guides/features/broadcast/weave.md): Send traces to W&B Weave
- [Webhook](https://openrouter.ai/docs/guides/features/broadcast/webhook.md): Send traces to any HTTP endpoint
- [Ori Eval](https://openrouter.ai/docs/guides/ori/eval.md): Find the best model for your project by testing your agent on real prompts, with one harness and one model for each run
- [Ori Harness](https://openrouter.ai/docs/guides/ori/harness.md): Run your existing agent CLI on OpenRouter with any model, organization guardrails, and one bill
- [Where Ori writes files](https://openrouter.ai/docs/guides/ori/files.md): Find the files and directories that Ori creates during a run
- [Data Collection](https://openrouter.ai/docs/guides/privacy/data-collection.md): What data OpenRouter collects
- [Provider Logging](https://openrouter.ai/docs/guides/privacy/provider-logging.md): Provider logging and data retention policies
- [Latency and Performance](https://openrouter.ai/docs/guides/best-practices/latency-and-performance.md): Understanding OpenRouter's performance characteristics
- [Prompt Caching](https://openrouter.ai/docs/guides/best-practices/prompt-caching.md): Cache prompt messages
- [Uptime Optimization](https://openrouter.ai/docs/guides/best-practices/uptime-optimization.md): OpenRouter tracks provider availability
- [Reasoning Tokens](https://openrouter.ai/docs/guides/best-practices/reasoning-tokens.md)
- [Provider Integration](https://openrouter.ai/docs/guides/community/for-providers.md)
- [Frameworks and Integrations Overview](https://openrouter.ai/docs/guides/community/frameworks-and-integrations-overview.md): Using OpenRouter with Popular Frameworks and Integrations
- [Awesome OpenRouter](https://openrouter.ai/docs/guides/community/awesome-openrouter.md): Community-curated list of projects built with OpenRouter
- [Effect AI SDK](https://openrouter.ai/docs/guides/community/effect-ai-sdk.md): Integrate OpenRouter using the Effect AI SDK
- [Arize AX](https://openrouter.ai/docs/guides/community/arize.md): Using OpenRouter with Arize AX
- [LangChain](https://openrouter.ai/docs/guides/community/langchain.md): Using OpenRouter with LangChain
- [LiveKit](https://openrouter.ai/docs/guides/community/livekit.md): Using OpenRouter with LiveKit Agents
- [Langfuse](https://openrouter.ai/docs/guides/community/langfuse.md): Using OpenRouter with Langfuse
- [Mastra](https://openrouter.ai/docs/guides/community/mastra.md): Using OpenRouter with Mastra
- [OpenAI SDK](https://openrouter.ai/docs/guides/community/openai-sdk.md): Using OpenRouter with OpenAI SDK
- [Anthropic Agent SDK](https://openrouter.ai/docs/guides/community/anthropic-agent-sdk.md): Using OpenRouter with the Anthropic Agent SDK
- [PydanticAI](https://openrouter.ai/docs/guides/community/pydantic-ai.md): Using OpenRouter with PydanticAI
- [Render](https://openrouter.ai/docs/guides/community/render.md): Using OpenRouter with Render Workflows
- [Replit](https://openrouter.ai/docs/guides/community/replit.md): Using OpenRouter with Replit Agent and Replit Apps
- [TanStack AI](https://openrouter.ai/docs/guides/community/tanstack-ai.md): Using OpenRouter with TanStack AI
- [Vercel AI SDK](https://openrouter.ai/docs/guides/community/vercel-ai-sdk.md): Using OpenRouter with Vercel AI SDK
- [Xcode](https://openrouter.ai/docs/guides/community/xcode.md): Using OpenRouter with Apple Intelligence in Xcode
- [Zapier](https://openrouter.ai/docs/guides/community/zapier.md): Build AI automations with OpenRouter & Zapier
- [Infisical](https://openrouter.ai/docs/guides/community/infisical.md): Automatic API Key Rotation with Infisical
- [API Reference](https://openrouter.ai/docs/api_reference/overview.md): An overview of OpenRouter's API
- [Streaming](https://openrouter.ai/docs/api_reference/streaming.md)
- [Embeddings](https://openrouter.ai/docs/api_reference/embeddings.md): Generate vector embeddings from text and images
- [Limits](https://openrouter.ai/docs/api_reference/limits.md): Credit Limits and Rate Limits
- [Authentication](https://openrouter.ai/docs/api_reference/authentication.md): API Authentication
- [Parameters](https://openrouter.ai/docs/api_reference/parameters.md)
- [Errors and Debugging](https://openrouter.ai/docs/api_reference/errors-and-debugging.md): API Errors and Debugging
- [Responses API](https://openrouter.ai/docs/api_reference/responses/overview.md): OpenAI-compatible Responses API
- [Basic Usage](https://openrouter.ai/docs/api_reference/responses/basic-usage.md): Getting started with the Responses API
- [Reasoning](https://openrouter.ai/docs/api_reference/responses/reasoning.md): Advanced reasoning capabilities with the Responses API
- [Tool Calling](https://openrouter.ai/docs/api_reference/responses/tool-calling.md): Function calling and tool integration with the Responses API
- [Web Search](https://openrouter.ai/docs/api_reference/responses/web-search.md): Real-time web search integration with the Responses API
- [Error Handling](https://openrouter.ai/docs/api_reference/responses/error-handling.md): Understanding and handling errors in the Responses API
- [API Versioning](https://openrouter.ai/docs/api_reference/versioning.md): How the OpenRouter API is versioned, what we consider a breaking change, and how deprecations are communicated.
- [API Changelog](https://openrouter.ai/docs/changelog.md): Changes to the OpenRouter API, generated from the OpenAPI specification on every release.
- [Client SDKs](https://openrouter.ai/docs/client-sdks/overview.md): Lightweight, type-safe clients for the OpenRouter API
- [Usage for Agents](https://openrouter.ai/docs/client-sdks/usage-for-agents.md): Add OpenRouter Client SDKs skills to your AI coding assistant
- [OpenRouter TypeScript SDK](https://openrouter.ai/docs/client-sdks/typescript/overview.md): Type-safe TypeScript toolkit for building AI features against 400+ models through OpenRouter.
- [Analytics](https://openrouter.ai/docs/client-sdks/typescript/sdks/analytics/README.md): Analytics and usage endpoints
- [APIKeys](https://openrouter.ai/docs/client-sdks/typescript/sdks/apikeys/README.md): API key management endpoints
- [Benchmarks](https://openrouter.ai/docs/client-sdks/typescript/sdks/benchmarks/README.md): Benchmarks endpoints
- [Beta.Responses](https://openrouter.ai/docs/client-sdks/typescript/sdks/betaresponses/README.md): Deprecated alias of responses. Use responses instead; scheduled for removal (sunset date TBD).
- [BYOK](https://openrouter.ai/docs/client-sdks/typescript/sdks/byok/README.md): BYOK endpoints
- [Chat](https://openrouter.ai/docs/client-sdks/typescript/sdks/chat/README.md)
- [Classifications](https://openrouter.ai/docs/client-sdks/typescript/sdks/classifications/README.md): Task classification market-share endpoints
- [Credits](https://openrouter.ai/docs/client-sdks/typescript/sdks/credits/README.md): Credit management endpoints
- [Datasets](https://openrouter.ai/docs/client-sdks/typescript/sdks/datasets/README.md): Public OpenRouter usage datasets. Data returned by these endpoints is licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/): reuse and republish it, including commercially, with attribution to OpenRouter.
- [Embeddings](https://openrouter.ai/docs/client-sdks/typescript/sdks/embeddings/README.md): Text embedding endpoints
- [Endpoints](https://openrouter.ai/docs/client-sdks/typescript/sdks/endpoints/README.md): Endpoint information
- [Files](https://openrouter.ai/docs/client-sdks/typescript/sdks/files/README.md): Files endpoints
- [Generations](https://openrouter.ai/docs/client-sdks/typescript/sdks/generations/README.md): Generation history endpoints
- [Guardrails](https://openrouter.ai/docs/client-sdks/typescript/sdks/guardrails/README.md): Guardrails endpoints
- [Images](https://openrouter.ai/docs/client-sdks/typescript/sdks/images/README.md): Images endpoints
- [Models](https://openrouter.ai/docs/client-sdks/typescript/sdks/models/README.md): Model information endpoints
- [OAuth](https://openrouter.ai/docs/client-sdks/typescript/sdks/oauth/README.md): OAuth authentication endpoints
- [Observability](https://openrouter.ai/docs/client-sdks/typescript/sdks/observability/README.md): Observability endpoints
- [Organization](https://openrouter.ai/docs/client-sdks/typescript/sdks/organization/README.md): Organization endpoints
- [Presets](https://openrouter.ai/docs/client-sdks/typescript/sdks/presets/README.md): Presets endpoints
- [Providers](https://openrouter.ai/docs/client-sdks/typescript/sdks/providers/README.md): Provider information endpoints
- [Rerank](https://openrouter.ai/docs/client-sdks/typescript/sdks/rerank/README.md): Rerank endpoints
- [Responses](https://openrouter.ai/docs/client-sdks/typescript/sdks/responses/README.md): OpenAI-compatible Responses API endpoints
- [STT](https://openrouter.ai/docs/client-sdks/typescript/sdks/stt/README.md): Speech-to-text endpoints
- [TTS](https://openrouter.ai/docs/client-sdks/typescript/sdks/tts/README.md): Text-to-speech endpoints
- [VideoGeneration](https://openrouter.ai/docs/client-sdks/typescript/sdks/videogeneration/README.md): Video Generation endpoints
- [Workspaces](https://openrouter.ai/docs/client-sdks/typescript/sdks/workspaces/README.md): Workspaces endpoints
- [OpenRouter Python SDK](https://openrouter.ai/docs/client-sdks/python/overview.md): Python SDK for building AI features against 400+ models through OpenRouter.
- [Analytics](https://openrouter.ai/docs/client-sdks/python/sdks/analytics/README.md): Analytics and usage endpoints
- [APIKeys](https://openrouter.ai/docs/client-sdks/python/sdks/apikeys/README.md): API key management endpoints
- [Benchmarks](https://openrouter.ai/docs/client-sdks/python/sdks/benchmarks/README.md): Benchmarks endpoints
- [Beta.Responses](https://openrouter.ai/docs/client-sdks/python/sdks/betaresponses/README.md): Deprecated alias for responses endpoints. Use responses instead. Scheduled for removal (sunset date TBD).
- [BYOK](https://openrouter.ai/docs/client-sdks/python/sdks/byok/README.md): BYOK endpoints
- [Chat](https://openrouter.ai/docs/client-sdks/python/sdks/chat/README.md)
- [Classifications](https://openrouter.ai/docs/client-sdks/python/sdks/classifications/README.md): Task classification market-share endpoints
- [Credits](https://openrouter.ai/docs/client-sdks/python/sdks/credits/README.md): Credit management endpoints
- [Datasets](https://openrouter.ai/docs/client-sdks/python/sdks/datasets/README.md): Public OpenRouter usage datasets. Data returned by these endpoints is licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/): reuse and republish it, including commercially, with attribution to OpenRouter.
- [Embeddings](https://openrouter.ai/docs/client-sdks/python/sdks/embeddings/README.md): Text embedding endpoints
- [Endpoints](https://openrouter.ai/docs/client-sdks/python/sdks/endpoints/README.md): Endpoint information
- [Files](https://openrouter.ai/docs/client-sdks/python/sdks/files/README.md): Files endpoints
- [Generations](https://openrouter.ai/docs/client-sdks/python/sdks/generations/README.md): Generation history endpoints
- [Guardrails](https://openrouter.ai/docs/client-sdks/python/sdks/guardrails/README.md): Guardrails endpoints
- [Images](https://openrouter.ai/docs/client-sdks/python/sdks/images/README.md): Images endpoints
- [Models](https://openrouter.ai/docs/client-sdks/python/sdks/models/README.md): Model information endpoints
- [OAuth](https://openrouter.ai/docs/client-sdks/python/sdks/oauth/README.md): OAuth authentication endpoints
- [Observability](https://openrouter.ai/docs/client-sdks/python/sdks/observability/README.md): Observability endpoints
- [Organization](https://openrouter.ai/docs/client-sdks/python/sdks/organization/README.md): Organization endpoints
- [Presets](https://openrouter.ai/docs/client-sdks/python/sdks/presets/README.md): Presets endpoints
- [Providers](https://openrouter.ai/docs/client-sdks/python/sdks/providers/README.md): Provider information endpoints
- [Rerank](https://openrouter.ai/docs/client-sdks/python/sdks/rerank/README.md): Rerank endpoints
- [Responses](https://openrouter.ai/docs/client-sdks/python/sdks/responses/README.md): OpenAI-compatible Responses API endpoints
- [Scim](https://openrouter.ai/docs/client-sdks/python/sdks/scim/README.md): SCIM endpoints
- [STT](https://openrouter.ai/docs/client-sdks/python/sdks/stt/README.md): Speech-to-text endpoints
- [TTS](https://openrouter.ai/docs/client-sdks/python/sdks/tts/README.md): Text-to-speech endpoints
- [VideoGeneration](https://openrouter.ai/docs/client-sdks/python/sdks/videogeneration/README.md): Video Generation endpoints
- [Workspaces](https://openrouter.ai/docs/client-sdks/python/sdks/workspaces/README.md): Workspaces endpoints
- [OpenRouter Go SDK](https://openrouter.ai/docs/client-sdks/go/overview.md): Go SDK for building AI features against 400+ models through OpenRouter.
- [Analytics](https://openrouter.ai/docs/client-sdks/go/sdks/analytics/README.md): Analytics and usage endpoints
- [APIKeys](https://openrouter.ai/docs/client-sdks/go/sdks/apikeys/README.md): API key management endpoints
- [Benchmarks](https://openrouter.ai/docs/client-sdks/go/sdks/benchmarks/README.md): Benchmarks endpoints
- [Beta.Responses](https://openrouter.ai/docs/client-sdks/go/sdks/betaresponses/README.md): Deprecated alias of responses. Use responses instead; scheduled for removal (sunset date TBD).
- [BYOK](https://openrouter.ai/docs/client-sdks/go/sdks/byok/README.md): BYOK endpoints
- [Chat](https://openrouter.ai/docs/client-sdks/go/sdks/chat/README.md)
- [Classifications](https://openrouter.ai/docs/client-sdks/go/sdks/classifications/README.md): Task classification market-share endpoints
- [Credits](https://openrouter.ai/docs/client-sdks/go/sdks/credits/README.md): Credit management endpoints
- [Datasets](https://openrouter.ai/docs/client-sdks/go/sdks/datasets/README.md): Public OpenRouter usage datasets. Data returned by these endpoints is licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/): reuse and republish it, including commercially, with attribution to OpenRouter.
- [Embeddings](https://openrouter.ai/docs/client-sdks/go/sdks/embeddings/README.md): Text embedding endpoints
- [Endpoints](https://openrouter.ai/docs/client-sdks/go/sdks/endpoints/README.md): Endpoint information
- [Files](https://openrouter.ai/docs/client-sdks/go/sdks/files/README.md): Files endpoints
- [Generations](https://openrouter.ai/docs/client-sdks/go/sdks/generations/README.md): Generation history endpoints
- [Guardrails](https://openrouter.ai/docs/client-sdks/go/sdks/guardrails/README.md): Guardrails endpoints
- [Images](https://openrouter.ai/docs/client-sdks/go/sdks/images/README.md): Images endpoints
- [Models](https://openrouter.ai/docs/client-sdks/go/sdks/models/README.md): Model information endpoints
- [OAuth](https://openrouter.ai/docs/client-sdks/go/sdks/oauth/README.md): OAuth authentication endpoints
- [Observability](https://openrouter.ai/docs/client-sdks/go/sdks/observability/README.md): Observability endpoints
- [Organization](https://openrouter.ai/docs/client-sdks/go/sdks/organization/README.md): Organization endpoints
- [Presets](https://openrouter.ai/docs/client-sdks/go/sdks/presets/README.md): Presets endpoints
- [Providers](https://openrouter.ai/docs/client-sdks/go/sdks/providers/README.md): Provider information endpoints
- [Rerank](https://openrouter.ai/docs/client-sdks/go/sdks/rerank/README.md): Rerank endpoints
- [Responses](https://openrouter.ai/docs/client-sdks/go/sdks/responses/README.md): OpenAI-compatible Responses API endpoints
- [Scim](https://openrouter.ai/docs/client-sdks/go/sdks/scim/README.md): SCIM endpoints
- [STT](https://openrouter.ai/docs/client-sdks/go/sdks/stt/README.md): Speech-to-text endpoints
- [TTS](https://openrouter.ai/docs/client-sdks/go/sdks/tts/README.md): Text-to-speech endpoints
- [VideoGeneration](https://openrouter.ai/docs/client-sdks/go/sdks/videogeneration/README.md): Video Generation endpoints
- [Workspaces](https://openrouter.ai/docs/client-sdks/go/sdks/workspaces/README.md): Workspaces endpoints
- [DevTools](https://openrouter.ai/docs/client-sdks/dev-tools/devtools.md): SDK Development Tools for telemetry capture and visualization
- [Migrating to @openrouter/agent](https://openrouter.ai/docs/client-sdks/agent-migration.md): Move agent toolkit imports from @openrouter/sdk to the standalone @openrouter/agent package
- [Agent SDK](https://openrouter.ai/docs/agent-sdk/overview.md): Build AI agents with multi-turn loops, tools, and conversation state
- [Usage for Agents](https://openrouter.ai/docs/agent-sdk/usage-for-agents.md): Add OpenRouter Agent SDK skills to your AI coding assistant
- [TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/overview.md): Official OpenRouter TypeScript SDK documentation
- [Analytics - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/analytics.md): Analytics method reference
- [APIKeys - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/apikeys.md): APIKeys method reference
- [Chat - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/chat.md): Chat method reference
- [Credits - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/credits.md): Credits method reference
- [Embeddings - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/embeddings.md): Embeddings method reference
- [Endpoints - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/endpoints.md): Endpoints method reference
- [Generations - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/generations.md): Generations method reference
- [Guardrails - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/guardrails.md): Guardrails method reference
- [Models - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/models.md): Models method reference
- [OAuth - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/oauth.md): OAuth method reference
- [Organization - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/organization.md): Organization method reference
- [Providers - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/providers.md): Providers method reference
- [Rerank - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/rerank.md): Rerank method reference
- [Beta.Responses - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/responses.md): Beta.Responses method reference
- [Speech - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/tts.md): Speech method reference
- [VideoGeneration - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/videogeneration.md): VideoGeneration method reference
- [Workspaces - TypeScript SDK](https://openrouter.ai/docs/agent-sdk/typescript/api-reference/workspaces.md): Workspaces method reference
- [Call Model (Typescript)](https://openrouter.ai/docs/agent-sdk/call-model/overview.md): A unified API for calling any LLM with automatic tool execution and multiple consumption patterns
- [Working with Items](https://openrouter.ai/docs/agent-sdk/call-model/items.md): Understanding the items-based streaming paradigm for callModel
- [Agent SDK API Reference](https://openrouter.ai/docs/agent-sdk/call-model/api-reference.md): Type signatures and exports for the Agent SDK, covering callModel, ModelResult, tool types, conversation state helpers, stop conditions, and format utilities.
- [Dynamic Parameters](https://openrouter.ai/docs/agent-sdk/call-model/dynamic-parameters.md): Use async functions for adaptive model behavior across turns
- [Next Turn Params](https://openrouter.ai/docs/agent-sdk/call-model/next-turn-params.md): Build encapsulated, context-aware tools with `nextTurnParams`. Create skills systems, plugins, and adaptive multi-turn agents.
- [Stop Conditions](https://openrouter.ai/docs/agent-sdk/call-model/stop-conditions.md): Control multi-turn execution with `stopWhen`. Use built-in helpers or custom conditions to stop by step count, tool calls, cost, or tokens.
- [Streaming](https://openrouter.ai/docs/agent-sdk/call-model/streaming.md): Stream responses in real-time with multiple consumption patterns. All streams are built on a reusable stream architecture that supports concurrent consumers.
- [Text Generation](https://openrouter.ai/docs/agent-sdk/call-model/text-generation.md): Generate text with callModel using various input formats and model configurations. Supports multiple consumption patterns including text, streaming, and structured output.
- [Message Formats](https://openrouter.ai/docs/agent-sdk/call-model/message-formats.md): The OpenRouter SDK provides helper functions to convert between popular message formats. This makes it easy to migrate existing code or integrate with different APIs.
- [Tools](https://openrouter.ai/docs/agent-sdk/call-model/tools.md): Define type-safe tools for callModel with Zod schemas, including regular, generator, manual, HITL, and MCP-branded tools, with automatic multi-turn execution.
- [Async Tools](https://openrouter.ai/docs/agent-sdk/call-model/async-tools.md): Run long-running tools in the background or defer them to external systems, while the model keeps working, checks progress, steers, and receives results automatically.
- [MCP tools](https://openrouter.ai/docs/agent-sdk/call-model/mcp-tools.md): Connect remote Model Context Protocol servers to the Agent SDK with @openrouter/mcp (auth, caching, streaming, resources, and elicitation).
- [Lifecycle Hooks](https://openrouter.ai/docs/agent-sdk/call-model/lifecycle-hooks.md): Observe and control the agent loop with typed lifecycle hooks.
- [Doom-Loop Detection](https://openrouter.ai/docs/agent-sdk/call-model/doom-loop-detection.md): Detect and act on agent runs that repeat the same tool calls, server-tool requests, or text without making progress.
- [Tool Approval & State Persistence](https://openrouter.ai/docs/agent-sdk/call-model/tool-approval-state.md): Add human-in-the-loop approval gates for sensitive tools and persist conversation state across callModel invocations.
- [Weather Tool](https://openrouter.ai/docs/agent-sdk/call-model/examples/weather-tool.md): A complete weather tool demonstrating external API integration, proper validation, and error handling.
- [Skills Loader](https://openrouter.ai/docs/agent-sdk/call-model/examples/skills-loader.md): A complete implementation of a skills system similar to Claude Code, demonstrating the power of `nextTurnParams` for context injection.
- [DevTools](https://openrouter.ai/docs/agent-sdk/dev-tools/devtools.md): SDK Development Tools for telemetry capture and visualization
- [Migrating to @openrouter/agent](https://openrouter.ai/docs/agent-sdk/agent-migration.md): Move agent toolkit imports from @openrouter/sdk to the standalone @openrouter/agent package
- [Quickstart: Build a Chat App](https://openrouter.ai/docs/cookbook/get-started/quickstart.md): Send your first message and stream a response with the OpenRouter SDK
- [Migrate to OpenRouter in One Prompt](https://openrouter.ai/docs/cookbook/get-started/migrate-to-openrouter.md): Move an existing app's LLM calls to OpenRouter with a single coding-agent prompt
- [Enterprise Onboarding Journey](https://openrouter.ai/docs/cookbook/get-started/enterprise-onboarding-journey.md): What to expect from signature to production, and what we need from you at each step
- [Enterprise Quickstart](https://openrouter.ai/docs/cookbook/get-started/enterprise-quickstart.md): Get your organization up and running with OpenRouter
- [Free Models Router](https://openrouter.ai/docs/cookbook/get-started/free-models-router-playground.md): Get started with free AI inference using the OpenRouter Chat Playground
- [Automatic Code Review](https://openrouter.ai/docs/cookbook/coding-agents/automatic-code-review.md): Automatic code review for Claude Code using hooks and OpenRouter — async, non-blocking reviews from a second model while you keep working
- [Claude Code](https://openrouter.ai/docs/cookbook/coding-agents/claude-code-integration.md): Use Claude Code with OpenRouter
- [Claude Desktop](https://openrouter.ai/docs/cookbook/coding-agents/claude-desktop-integration.md): Use Claude Desktop with OpenRouter
- [Codex CLI](https://openrouter.ai/docs/cookbook/coding-agents/codex-cli.md): Use Codex CLI with OpenRouter
- [Cursor](https://openrouter.ai/docs/cookbook/coding-agents/cursor-integration.md): Use Cursor with OpenRouter
- [Hermes Agent](https://openrouter.ai/docs/cookbook/coding-agents/hermes-integration.md): Use Hermes Agent by Nous Research with OpenRouter
- [Junie CLI](https://openrouter.ai/docs/cookbook/coding-agents/junie.md): Using OpenRouter with JetBrains Junie CLI
- [Using MCP Servers with OpenRouter](https://openrouter.ai/docs/cookbook/coding-agents/mcp-servers.md): Use MCP Servers with OpenRouter
- [OpenClaw 🦞](https://openrouter.ai/docs/cookbook/coding-agents/openclaw-integration.md): Use OpenClaw (formerly Moltbot, formerly Clawdbot) with OpenRouter
- [OpenCode](https://openrouter.ai/docs/cookbook/coding-agents/opencode-integration.md): Use OpenCode with OpenRouter
- [Add Human-in-the-Loop Controls to an Agent SDK Agent](https://openrouter.ai/docs/cookbook/building-agents/hitl-tools.md): Add HITL to an existing Agent SDK agent so it can pause high-stakes tool calls for human input
- [Build a Long-Horizon Agent](https://openrouter.ai/docs/cookbook/building-agents/long-horizon-agents.md): Run multi-hour agent loops with cost ceilings, resumable state, and voice input
- [Build a Token-Efficient Review Agent](https://openrouter.ai/docs/cookbook/building-agents/advisor-server-tool.md): Use a cheap executor model for routine work and call Advisor only for compact uncertainty checks
- [Delegate Routine Work to Cheaper Models](https://openrouter.ai/docs/cookbook/building-agents/subagent-server-tool.md): Use an orchestrator for planning and a cheap subagent worker for each subtask
- [Build Your Own Agent TUI](https://openrouter.ai/docs/cookbook/building-agents/create-agent-harness-tui.md): Scaffold a custom AI agent with a fully customizable terminal interface using an AI coding agent
- [Build Your Own Headless Agent](https://openrouter.ai/docs/cookbook/building-agents/create-headless-agent.md): Scaffold a headless AI agent for CLI tools, API servers, and automation pipelines
- [Choose a Video Generation Model](https://openrouter.ai/docs/cookbook/video-generation/choose-video-model.md): Select an OpenRouter video model by matching clip requirements and scoring priorities
- [Generate and Download a Video from Text](https://openrouter.ai/docs/cookbook/video-generation/text-to-video.md): Submit a text-to-video job, poll for completion, and save the generated MP4
- [Get Video Results with Webhooks](https://openrouter.ai/docs/cookbook/video-generation/video-generation-webhooks.md): Submit a video job with a callback URL and verify OpenRouter webhook signatures
- [Guide a Video with Reference Images](https://openrouter.ai/docs/cookbook/video-generation/reference-to-video.md): Use reference images to influence video subject, style, or identity without exact frame control
- [Turn an Image into a Video](https://openrouter.ai/docs/cookbook/video-generation/image-to-video.md): Use frame images to control the first or last frame of an OpenRouter video
- [Use Provider-Specific Video Options](https://openrouter.ai/docs/cookbook/video-generation/provider-specific-video-options.md): Inspect allowed passthrough parameters and send provider-specific video controls safely
- [Enhance Image Generation with Presets](https://openrouter.ai/docs/cookbook/image-generation/preset-enhanced-images.md): Pair a text model with the image generation server tool so every request gets a refined prompt automatically
- [Distillation](https://openrouter.ai/docs/cookbook/evaluate-and-optimize/distillation.md): Ensure compliance with provider and model creator policies for distillation
- [Claude Opus 5 Migration Guide](https://openrouter.ai/docs/cookbook/evaluate-and-optimize/model-migrations/opus-5.md): Migrate to Claude Opus 5 — reasoning on by default, effort restrictions when disabling reasoning, and mid-conversation tool changes
- [Claude 5 Sonnet Migration Guide](https://openrouter.ai/docs/cookbook/evaluate-and-optimize/model-migrations/sonnet-5.md): Migrate to Claude 5 Sonnet — sampling parameters removed, adaptive-only thinking, and the new xhigh effort level
- [Claude 4.7 Migration Guide](https://openrouter.ai/docs/cookbook/evaluate-and-optimize/model-migrations/claude-4-7.md): Migrate to Claude 4.7 Opus — sampling parameters removed, adaptive-only thinking, and new xhigh effort level
- [Claude 4.6 Migration Guide](https://openrouter.ai/docs/cookbook/evaluate-and-optimize/model-migrations/claude-4-6.md): Migrate to Claude 4.6 with adaptive thinking and max effort level
- [GPT-5.6 Migration Guide](https://openrouter.ai/docs/cookbook/evaluate-and-optimize/model-migrations/gpt-5-6.md): Adopt reasoning.mode, reasoning.context, and explicit prompt caching for the GPT-5.6 model family
- [GPT-5.4 Migration Guide](https://openrouter.ai/docs/cookbook/evaluate-and-optimize/model-migrations/gpt-5-4.md): Support the phase field for GPT-5.3 Codex, GPT-5.4, GPT-5.4 Pro, GPT-5.5, and GPT-5.5 Pro
- [RAG with Embeddings & Rerank](https://openrouter.ai/docs/cookbook/evaluate-and-optimize/rag.md): Build retrieval-augmented generation pipelines using OpenRouter's embeddings and rerank APIs
- [Red Teaming](https://openrouter.ai/docs/cookbook/evaluate-and-optimize/red-teaming.md): Policy for red teaming and adversarial testing on OpenRouter
- [Activity Export](https://openrouter.ai/docs/cookbook/administration/activity-export.md)
- [API Key Rotation](https://openrouter.ai/docs/cookbook/administration/api-key-rotation.md): Securely rotate your OpenRouter API keys
- [Control Costs with the Analytics API](https://openrouter.ai/docs/cookbook/administration/analytics-cost-control.md): Hand your coding agent a management key and the analytics skill, then ask it where your money is going
- [Crypto API](https://openrouter.ai/docs/cookbook/administration/crypto-api.md): Coinbase Commerce API deprecation
- [Data API](https://openrouter.ai/docs/cookbook/administration/data-api.md)
- [Organization Management](https://openrouter.ai/docs/cookbook/administration/organization-management.md): Manage teams and shared resources with OpenRouter organizations
- [Adding a Tax ID to Your Invoices](https://openrouter.ai/docs/cookbook/administration/tax-id.md): How to add your VAT, GST, or other tax ID so it appears on OpenRouter invoices
- [Usage Accounting](https://openrouter.ai/docs/cookbook/administration/usage-accounting.md)
- [User Tracking](https://openrouter.ai/docs/cookbook/administration/user-tracking.md)

## OpenAPI Specs

- [openapi](https://openrouter.ai/docs/openapi/openapi.yaml)
- [provider-monitor-schema-v2.openapi](https://openrouter.ai/docs/assets/provider-monitor-schema-v2.openapi.json)
