Inworld Router

Reason in realtime. Route to the best model and tools for every user and context

Intelligently route requests across OpenAI, Anthropic, Google, and 200+ models through a single API. Built-in analytics to ensure the metrics you care about improve. No latency added. Built-in failover, A/B testing, and intelligent model selection with no code changes required.

Get Started See models Read the docs

curl 'https://api.inworld.ai/v1/chat/completions' \
  -H "Content-Type: application/json" \
  -H "Authorization: Basic $INWORLD_API_KEY" \
  -d '{

    "model": "inworld/user-aware",

    "messages": [{"role": "user", "content": "Hello"}],
    "extra_body": {
        "metadata": {
            "language": "es",
            "country": "MX",
            "plan": "free"
        }
    }
  }'

curl 'https://api.inworld.ai/v1/chat/completions' \
  -H "Content-Type: application/json" \
  -H "Authorization: Basic $INWORLD_API_KEY" \
  -d '{

    "model": "inworld/context-aware",

    "messages": [
        {"role": "system", "content": "You are a support agent."},
        {"role": "user", "content": "My order never arrived"}
    ],
    "extra_body": {
        "metadata": {
            "intent": "complaint",
            "emotion": "frustrated",
            "session_turns": 4
        }
    }
  }'

Intelligent reasoning over every request

One integration. Every model. No latency added, made for realtime. Inworld Router handles reliability, cost, traffic splitting, and model selection, so you don't have to.

Unified API

Access OpenAI, Anthropic, Google, Mistral, and more through a single endpoint.

Automatic Failover

When a provider returns an error, Router instantly retries the next model in the chain.

Context and User-Aware Routing

Route to different models based on any custom metadata, or let Router pick the best option for each request.

Multimodal

Route requests with text, audio, image, code, and more. Add Inworld TTS for voice pipelines.

A/B Testing

Split traffic by weight with sticky user assignment. Ramp new models gradually without a deploy.

Integrated Analytics

Per-request logs with model selected, TTFT, cost per token, and the full attempt chain including failovers.

Use cases

Common patterns for Inworld Router in production. Each one maps to a real configuration you can copy and adapt.

curl 'https://api.inworld.ai/v1/chat/completions' \
  -H "Authorization: Basic $INWORLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "inworld/user-aware",
    "messages": [{"role": "user", "content": "Hola, necesito ayuda"}],
    "extra_body": {
      "metadata": {
        "language": "es",
        "country": "MX",
        "plan": "free"
      }
    }
  }'

curl 'https://api.inworld.ai/router/v1/routers' \
  -H "Authorization: Basic $INWORLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "displayName": "User-Aware",
    "routes": [
      {
        "condition": {
          "cel_expression": "language == \"es\""
        },
        "route": {
          "variants": [
            { "variant": { "modelId": "openai/gpt-5.2" }, "weight": 100 }
          ]
        }
      },
      {
        "condition": {
          "cel_expression": "plan == \"free\""
        },
        "route": {
          "variants": [
            { "variant": { "modelId": "anthropic/claude-haiku-4-5" }, "weight": 100 }
          ]
        }
      }
    ],
    "defaultRoute": {
      "variants": [
        { "variant": { "modelId": "anthropic/claude-sonnet-4-6" }, "weight": 100 }
      ]
    }
  }'

curl 'https://api.inworld.ai/v1/chat/completions' \
  -H "Authorization: Basic $INWORLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "inworld/user-aware",
    "messages": [{"role": "user", "content": "Hola, necesito ayuda"}],
    "extra_body": {
      "metadata": {
        "language": "es",
        "country": "MX",
        "plan": "free"
      }
    }
  }'

curl 'https://api.inworld.ai/router/v1/routers' \
  -H "Authorization: Basic $INWORLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "displayName": "User-Aware",
    "routes": [
      {
        "condition": {
          "cel_expression": "language == \"es\""
        },
        "route": {
          "variants": [
            { "variant": { "modelId": "openai/gpt-5.2" }, "weight": 100 }
          ]
        }
      },
      {
        "condition": {
          "cel_expression": "plan == \"free\""
        },
        "route": {
          "variants": [
            { "variant": { "modelId": "anthropic/claude-haiku-4-5" }, "weight": 100 }
          ]
        }
      }
    ],
    "defaultRoute": {
      "variants": [
        { "variant": { "modelId": "anthropic/claude-sonnet-4-6" }, "weight": 100 }
      ]
    }
  }'

FAQ

Yes. Migration guides are available for OpenRouter and Anthropic-based setups. The core change is updating your base_url and API key, while your existing request structure stays the same.

Router provides access to hundreds of models from leading providers, such as OpenAI, Anthropic, Google, and many more. You can see the full model list here.

While Router is in Research Preview, you pay provider rates directly, with no markup or margin added. Rates for all models are available here.

Inworld Router itself doesn't impose additional rate limits on top of providers. Provider-level rate limits are handled automatically by retrying the next model in your fallback chain.

Most gateways give you a unified API and basic fallback. Inworld Router offers more control and lets you run real experiments: conditional routing, dynamic tiering, traffic splitting by percentage, sticky user assignment, with results pushed to your analytics platform of choice.