# OpenRouter

- Status: Unclaimed: compiled by Nowen from public sources, not reviewed by the company
- Industry: AI Infrastructure
- Delivery model: software
- Website: https://openrouter.ai
- Legal name: OpenRouter, Inc.
- AI agent profile: https://nowen.ai/agents/openrouter-ai
- Updated: 2026-10-30
- Directory: one of 5 AI agents in AI Infrastructure (https://nowen.ai/industry/ai-infrastructure)
- Read by AI assistants from: Perplexity, Amazon

> OpenRouter helps developers and organizations access, route, and manage AI models from multiple providers through a unified platform.

OpenRouter provides developers and organizations with a unified way to access and compare AI models from multiple providers. Its infrastructure supports model routing, automatic failover, cost tracking, and organizational controls, helping teams build and operate AI applications while reducing dependence on any single provider.

**Mission:** Our mission is to increase AI neurodiversity.

## Products & Services

### [OpenRouter API](https://openrouter.ai/developers)
*Platform*
Access and compare models through one API while simplifying integrations, routing around provider issues, and tracking usage and costs.
OpenRouter API provides a unified, OpenAI-compatible interface for accessing hundreds of AI models across multiple providers. Developers can use one API key and consistent request formats to switch models without changing their integration. OpenRouter can route requests based on price, throughput, latency, and reliability, and automatically retry through other providers when failures or rate limits occur. The API supports streaming, tool calling, structured outputs, and models for text, images, video, and audio. Developers can also configure provider preferences, data policies, and regional routing, and track usage and costs across their requests.

- **Unified model access** — Access Hundreds Of Models
- **Automatic provider routing** — Route Requests To Suitable Providers
- **OpenAI-compatible integration** — Reuse Familiar API Integrations
- **Automatic provider and model failover** — Retry Through Available Providers
- **Data policy controls** — Apply Data And Provider Policies
- **Multimodal inference** — Build Across Multiple Modalities
- **Streaming and tool calling** — Stream Responses And Call Tools
- **In-region routing** — Keep Inference Within A Region
- **Usage and cost tracking** — Track Usage And Costs
- **Structured outputs** — Request Structured JSON Responses
- **API plugins** — Extend Model Capabilities

### [OpenRouter Chat](https://openrouter.ai/chat)
*Product*
Compare responses from hundreds of AI models on the same prompt in one interface to evaluate options efficiently.
OpenRouter Chat is a playground for testing and evaluating responses from OpenAI, Google, Anthropic, and more than 600 AI models in one chat interface. Choose one or more models, send the same message to each, and read their responses side by side. Responses are AI-generated and may be inaccurate, so review them before relying on them.

- **Side-by-side model comparison** — Compare Responses Side By Side
- **Access to multiple models** — Access Hundreds Of AI Models

### [OpenRouter Business](https://openrouter.ai/business)
*Product*
Keep inference in the EU or US while giving teams expanded workspace capacity, identity options, spend controls, and operational alerts.
OpenRouter Business is a self-serve plan for routing inference requests to providers in the EU or US, using the same API key and account. It also includes expanded workspaces, advanced notifications, workload identity federation, and guardrails and spend controls. The plan costs 8% on credit purchases, with no monthly minimum or contract. Its DPA applies through the Terms of Service, and organizations can request a signed copy.

- **EU and US in-region routing** — Keep Inference Within Your Chosen Region
- **Data-region guardrails** — Enforce Allowed Request Regions
- **Workspace capacity** — Separate Up To 1,000 Workspaces
- **Workload identity federation** — Authenticate Services With Identity Provider Tokens
- **Guardrails and spend controls** — Apply Guardrails And Manage Spend
- **Advanced notifications** — Send Operational Alerts To Your Team
- **Credit-purchase pricing** — Pay Only An 8% Credit-Purchase Fee
- **Organizational data processing agreement** — Document Your Data Processing Terms

### [OpenRouter Enterprise](https://openrouter.ai/enterprise)
*Platform*
Gives organizations governed access to hundreds of AI models through one gateway, with resilient routing, spend oversight, security controls, and consolidated enterprise procurement.
OpenRouter Enterprise is an AI gateway and inference control plane that gives organizations access to 600+ models across 80+ providers through one API. It offers model and provider routing, automatic failover, spend controls, security and data policies, and enterprise identity and reporting features. Enterprise agreements include invoiced billing options, credit lines, an SLA, priority support, and a dedicated engineering contact.

- **Unified model access** — Access Hundreds Of Models Through One API
- **Data policy enforcement** — Enforce Data Policies On Every Request
- **Task-based model routing** — Match Models To Each Task
- **Provider routing** — Route Requests By Price And Performance
- **Automatic failover** — Retry Requests Across Providers And Models
- **Spend controls and alerts** — Set Budgets And Track Spend
- **Regional data routing** — Keep Inference Within Your Chosen Region
- **Enterprise identity management** — Manage Team And Service Access
- **Enterprise billing and procurement** — Consolidate Provider Billing And Contracts
- **Provider key management** — Use Your Provider Keys And Capacity
- **Unified request reporting** — Review And Export Organization-Wide Usage
- **Enterprise support and SLA** — Get Priority Support And An SLA
- **Compliance documentation** — Support Security And Legal Reviews

### [OpenRouter Client SDKs](https://openrouter.ai/docs/client-sdks/overview)
*Product*
Build with OpenRouter models using typed clients that reduce boilerplate and provide consistent capabilities across TypeScript, Python, and Go.
Typed client libraries for TypeScript, Python, and Go that wrap the OpenRouter API. The SDKs provide full type safety, types generated from the OpenAPI specification, and a lean layer over the REST API. They support streaming, tool calls, structured output, and embeddings, with consistent behavior across languages. Use them to access OpenRouter models through a single client integration.

- **Multi-language clients** — Choose Your Language
- **Type-safe API access** — Write With Typed Clients
- **Consistent streaming** — Stream Across Languages
- **Consistent tool calls** — Handle Tool Calls Consistently
- **Consistent structured output** — Use Structured Output
- **Embeddings support** — Access Embeddings
- **Regional endpoint configuration** — Configure A Regional Endpoint

### [OpenRouter Agent SDK](https://openrouter.ai/docs/agent-sdk/overview)
*Product*
Build agents with less orchestration by automating multi-turn tool execution and state while routing model calls across providers.
The OpenRouter Agent SDK (@openrouter/agent) provides higher-level primitives for building AI agents that use OpenRouter models. Its callModel function manages multi-turn conversation loops, tool execution, and state, while supporting type-safe tools, streaming, and stop conditions. Agents can route calls across providers through OpenRouter. The SDK is available for TypeScript and Python, with Go in beta.

- **Multi-turn agent loops** — Automate Multi-Turn Agent Loops
- **Tool execution** — Run Tools Within Agent Loops
- **Multi-provider model routing** — Route Agent Calls Across Providers
- **Type-safe tool definitions** — Define Tools With Typed Inputs
- **Agent state management** — Manage Agent State Automatically
- **Streaming support** — Stream Agent Responses
- **Agent stop conditions** — Set Agent Stop Conditions
- **SDK language support** — Build Agents In Multiple Languages

### [OpenRouter Terraform Provider](https://openrouter.ai/docs/guides/overview/terraform)
*Product*
Manage OpenRouter configuration as code to make platform changes repeatable and reviewable.
The OpenRouter Terraform Provider lets teams manage OpenRouter as infrastructure-as-code, with repeatable and reviewable configuration for their platform.

- **Infrastructure-as-code configuration** — Manage OpenRouter As Code

### [OpenRouter DevTools](https://openrouter.ai/docs/client-sdks/dev-tools/devtools)
*Product*
Review and replay SDK activity locally to inspect requests, token counts, and errors during development.
OpenRouter DevTools captures SDK telemetry during development and lets you review and replay requests in a local web viewer, including their token counts and errors.

- **SDK telemetry capture** — Capture SDK Telemetry
- **Local request viewer** — Inspect Requests Locally
- **Request replay** — Replay Captured Requests

### [OpenRouter MCP Server](https://openrouter.ai/docs/guides/overview/mcp-server)
*Product*
Connect AI assistants to OpenRouter models and current platform information without installing a server or relying on stale reference data.
OpenRouter’s remote-hosted Model Context Protocol server connects compatible clients, including Claude Code and Cursor, to OpenRouter’s catalog of more than 600 models. Coding assistants can also retrieve live information about available models, pricing, credit balance, and usage rankings, and search OpenRouter documentation. Connect by adding the server URL to an MCP client and approving an OAuth login; there is nothing to install.

- **MCP client model access** — Access 600+ Models
- **Live model availability lookup** — Check Available Models
- **Remote hosting and OAuth connection** — Connect Without Installing
- **Live model pricing lookup** — Check Model Prices
- **OpenRouter documentation search** — Search OpenRouter Docs
- **Credit balance lookup** — Check Credit Balance
- **Usage ranking lookup** — View Usage Rankings

### [Ori Harness](https://openrouter.ai/ori/harness)
*Product*
Run familiar agent CLIs with OpenRouter models, existing organization policies, and consolidated usage tracking.
Ori Harness is a command-line tool that runs supported agent CLIs through OpenRouter, giving them access to OpenRouter models and organization settings. Launch agents such as Claude Code, Codex, Grok Build, Hermes, OpenCode, Pi, Cline, and others with the ori command. Choose an OpenRouter model while passing the rest of your command and flags through to the agent unchanged. Sign in with OAuth using an existing OpenRouter account, apply organization guardrails to requests, and view usage and spend from agents in the OpenRouter dashboard.

- **Agent CLI compatibility** — Run Familiar Agent CLIs
- **OpenRouter model selection** — Choose From OpenRouter Models
- **Organization guardrails** — Enforce Organization Policies
- **OAuth sign-in** — Sign In With Your OpenRouter Account
- **Consolidated usage and billing** — Track Agent Spend In One Place
- **Agent installation assistance** — Install Missing Agents With Guidance

### [Ori Code](https://openrouter.ai/ori#code)
*Product*
Work with multiple OpenRouter models from a native terminal coding agent.
Ori Code is OpenRouter’s native coding agent for the terminal, built from the ground up for working with multiple models through OpenRouter. It provides a terminal experience crafted specifically for that workflow.

- **Native terminal coding agent** — Work With Models In The Terminal
- **Multi-model support** — Choose From Multiple OpenRouter Models

### [Ori Eval](https://openrouter.ai/ori/eval)
*Product*
Find and compare models using evaluations based on your project’s own prompts, with results that help you weigh performance, time, and cost.
Ori Eval helps teams identify the best model for their project by using an agent to find relevant test material in their code, write evaluations, and run selected models against them. It ranks candidates using evaluation results, with scores, run times, and costs available for comparison. Evaluations run on a pinned harness and model, and can use LLM-as-judge grading.

- **Ranked model recommendations** — Rank Models By Evaluation Results
- **Project-specific test material discovery** — Find Relevant Project Prompts
- **Cross-model evaluation** — Test Models On Your Prompts
- **Evaluation authoring** — Create Project-Based Evaluations
- **Pinned evaluation setup** — Keep Evaluation Runs Consistent
- **LLM-as-judge grading** — Grade Model Outputs

### [Ori Intern](https://openrouter.ai/ori#intern)
*Product*
Help teams delegate work in Slack using model-flexible interns that learn reusable skills and can improve across the organization.
Ori Intern lets teams deploy agents in Slack that can use any model. Interns learn and build skills naturally, and those skills can be shared across interns so teams can improve together. Skills work across models, helping teams delegate work using a cost-optimal model. Ori Intern is in private testing and available through a waitlist.

- **Slack agent deployment** — Delegate Work From Slack
- **Flexible model use** — Use Skills Across Models
- **Natural skill learning** — Build Skills Through Work
- **Shared skills** — Share Skills Across Interns
- **Cost-optimal model delegation** — Choose Cost-Optimal Models

### [Ori Desktop](https://openrouter.ai/ori#desktop)
*Product*
Send tasks to OpenRouter models from your Mac and manage their sessions and approvals in one desktop experience.
Ori Desktop is an upcoming, OS-native Mac experience for sending tasks to OpenRouter models. Tasks run with Ori and can use any harness across hundreds of models. Users can create tasks from the menu bar, manage sessions, and make approvals. The product is currently available by waitlist.

- **Mac desktop task execution** — Run Tasks From Your Mac
- **Model and harness flexibility** — Choose Models And Harnesses
- **Menu bar task creation** — Create Tasks From The Menu Bar
- **Session management** — Manage Task Sessions
- **Task approvals** — Make Task Approvals

### [OpenRouter Data API](https://openrouter.ai/data)
*Product*
Access aggregated daily model usage rankings as JSON to work with OpenRouter’s public rankings data programmatically.
The OpenRouter Data API provides JSON access to the same aggregated usage data that powers OpenRouter’s public rankings. It returns the top 50 models per day by total token usage and authenticates with an existing OpenRouter API key. OpenRouter describes shared data as aggregated usage trends and says it does not sell prompt data.

- **Daily model usage rankings** — Retrieve Daily Model Rankings
- **JSON data access** — Access Rankings Data As JSON
- **OpenRouter API key authentication** — Authenticate With Your Existing API Key
- **Aggregated usage data** — Use Aggregated Usage Trends

## Market Segments

- **LLM gateways** (market size $300M, CAGR 30%): Infrastructure for routing application requests across LLM providers through a unified interface, supporting provider portability and structured generation.
  - Products: OpenRouter API, OpenRouter Business, OpenRouter Enterprise, OpenRouter Client SDKs, OpenRouter MCP Server, Ori Harness
- **AI governance** (market size $890M, CAGR 45.3%): Runtime controls that let enterprises enforce access permissions, isolate provider credentials, and apply hierarchical usage policies before AI requests reach configured providers.
  - Products: OpenRouter Business, OpenRouter Enterprise, OpenRouter API, Ori Harness
- **LLM evaluation** (market size $700M, CAGR 25%): Comparison of model responses, task performance, latency, and costs to support model selection, using side-by-side testing or project-specific evaluations.
  - Products: Ori Eval, OpenRouter Chat
- **AI coding assistants** (market size $1.0B, CAGR 35%): Agent-based assistance for software development through terminal workflows, with model selection across multiple providers.
  - Products: Ori Code

## Sources

- [OpenRouter](https://openrouter.ai)
- [OpenRouter API](https://openrouter.ai/developers)
- [OpenRouter Chat](https://openrouter.ai/chat)
- [OpenRouter Business](https://openrouter.ai/business)
- [OpenRouter Enterprise](https://openrouter.ai/enterprise)
- [OpenRouter Client SDKs](https://openrouter.ai/docs/client-sdks/overview)
- [OpenRouter Agent SDK](https://openrouter.ai/docs/agent-sdk/overview)
- [OpenRouter Terraform Provider](https://openrouter.ai/docs/guides/overview/terraform)
- [OpenRouter DevTools](https://openrouter.ai/docs/client-sdks/dev-tools/devtools)
- [OpenRouter MCP Server](https://openrouter.ai/docs/guides/overview/mcp-server)
- [Ori Harness](https://openrouter.ai/ori/harness)
- [Ori Code](https://openrouter.ai/ori#code)
- [Ori Eval](https://openrouter.ai/ori/eval)
- [Ori Intern](https://openrouter.ai/ori#intern)
- [Ori Desktop](https://openrouter.ai/ori#desktop)
- [OpenRouter Data API](https://openrouter.ai/data)
- [Market Size Base Year (Billions) ~USD 0.89 (2024); Growth Rate CAGR of 45.3% from 2024 to 2029.](https://www.marketsandmarkets.com/Market-Reports/geography/ai-governance-market/uk)
- [The global AI code tools market size was valued at USD 7.93 billion in 2025 and is projected to surge to USD 91.09 billion by 2035, expanding at a compound annual growth rate (CAGR) of 27.65%.](https://www.linkedin.com/pulse/ai-code-tools-market-size-surpass-usd-9109-billion-2jasf)