For the complete documentation index, see llms.txt. Markdown versions of all docs pages are available by appending .md to any docs URL.

Route agentgateway LLM traffic to Anthropic’s Claude models.

Configure Anthropic (Claude models) as an LLM provider in agentgateway.

Configuration

For the common API key case, use the following config. Use the AWS SigV4 section later in the page only when you need Claude Platform on AWS or custom signing behavior.

You can add the model in the UI or in your configuration file.

# yaml-language-server: $schema=https://agentgateway.dev/schema/config
llm:
  models:
  - name: "anthropic/*"
    provider: anthropic
    params:
      apiKey: "$ANTHROPIC_API_KEY"
    transformation:
      model: llmRequest.model.stripPrefix("anthropic/")

Example request

After you run agentgateway with the configuration from the previous section, send a request to the v1/messages endpoint. The forwarded request includes the x-api-key authorization header. If the client sends no anthropic-version header, the request uses the default 2023-06-01 version. If the client sends its own anthropic-version header, that value is forwarded to Anthropic. The Anthropic API returns the response to the client.

curl -X POST http://localhost:4000/v1/messages \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4-6",
    "max_tokens": 100,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Example response:

{
  "model": "claude-opus-4-6",
  "usage": {
    "input_tokens": 9,
    "output_tokens": 21,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0,
    "cache_creation": {
      "ephemeral_5m_input_tokens": 0,
      "ephemeral_1h_input_tokens": 0
    },
    "service_tier": "standard"
  },
  "content": [
    {
      "text": "Hi there! How are you doing today? Is there anything I can help you with?",
      "type": "text"
    }
  ],
  "id": "msg_01QdUEuzvXfjLh1HfMQd4UHP",
  "type": "message",
  "role": "assistant",
  "stop_reason": "end_turn",
  "stop_sequence": null
}

Send inline files through Chat Completions

In a /v1/chat/completions request to Anthropic, agentgateway converts an inline file content part to an Anthropic document block. For the required file.file_data format and the file parts that the conversion rejects, see File parts on a converted route.

Token counting

Use Anthropic’s count_tokens API to estimate token usage before you make a request. If the client sends an anthropic-version header, the request uses that value. If the client sends no version header, the request uses the default 2023-06-01 version. The request is formatted for Anthropic’s API.

curl -X POST http://localhost:4000/v1/messages/count_tokens \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4-6",
    "messages": [{"role": "user", "content": "Hello!"}],
    "system": "You are a helpful assistant."
  }'

Example response:

{
  "input_tokens": 15
}

Extended thinking and reasoning

Extended thinking and reasoning lets Claude reason through complex problems before generating a response. You can opt in to extended thinking and reasoning by adding specific parameters to your request.

This section describes a route that reaches the Anthropic Messages API directly. When a Chat Completions client reaches Anthropic, the request is converted to the Messages format, and thinking history is carried across turns only when the client sends back reasoning_signature. For details, see Reasoning carryover on a converted route.

To opt in to extended thinking, include the thinking.type field in your request. You can also set the output_config.effort field to control how much reasoning the model applies.

The following values are supported:

thinking field

output_config field

output_config has two independent sub-fields. You can use either or both.

The following example request uses adaptive extended thinking. Note that this setting requires the output_config.effort field to be set too.

curl "localhost:4000/v1/messages" -H content-type:application/json -d '{
  "model": "anthropic/claude-opus-4-6",
  "max_tokens": 1024,
  "thinking": {
    "type": "adaptive"
  },
  "output_config": {
    "effort": "high"
  },
  "messages": [
    {
      "role": "user",
      "content": "Explain the trade-offs between consistency and availability in distributed systems."
    }
  ]
}' | jq

Example output:

{
  "id": "msg_01HVEzWf4NJrsKyVeEUDnHNW",
  "type": "message",
  "role": "assistant",
  "model": "claude-opus-4-6",
  "content": [
    {
      "type": "thinking",
      "thinking": "Let me think through the trade-offs between consistency and availability..."
    },
    {
      "type": "text",
      "text": "# Consistency vs. Availability in Distributed Systems\n\n..."
    }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 21,
    "output_tokens": 1024
  }
}

Structured outputs

Structured outputs constrain the model to respond with a specific JSON schema. You must provide the schema definition in your request.

Provide the JSON schema definition in the output_config.format field.

curl "localhost:4000/v1/messages" -H content-type:application/json -d '{
  "model": "anthropic/claude-opus-4-6",
  "max_tokens": 256,
  "output_config": {
    "format": {
      "type": "json_schema",
      "schema": {
        "type": "object",
        "properties": {
          "answer": { "type": "string" },
          "confidence": { "type": "number" }
        },
        "required": ["answer", "confidence"],
        "additionalProperties": false
      }
    }
  },
  "messages": [
    {
      "role": "user",
      "content": "Is the sky blue? Respond with your answer and a confidence score between 0 and 1."
    }
  ]
}' | jq

Example output:

{
  "id": "msg_01PsCxtLN1vftAKZgvWXhCan",
  "type": "message",
  "role": "assistant",
  "model": "claude-opus-4-6",
  "content": [
    {
      "type": "text",
      "text": "{\"answer\":\"Yes, the sky is blue during clear daytime conditions.\",\"confidence\":0.98}"
    }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 29,
    "output_tokens": 28
  }
}

Use Claude Platform on AWS

Claude Platform on AWS hosts Anthropic’s native Messages API on AWS infrastructure at aws-external-anthropic.{region}.api.aws. Because the API is the same Anthropic Messages API, you point the anthropic provider at the AWS endpoint and choose either API-key or AWS SigV4 authentication.

# yaml-language-server: $schema=https://agentgateway.dev/schema/config

llm:
  models:
  - name: "*"
    provider: anthropic
    requestHeaders:
      set:
        # Replace with your workspace ID
        anthropic-workspace-id: wrkspc_XXXXX
    params:
      apiKey: $ANTHROPIC_AWS_API_KEY
      # Replace with your region
      baseUrl: https://aws-external-anthropic.us-west-2.api.aws/v1

# yaml-language-server: $schema=https://agentgateway.dev/schema/config

llm:
  models:
  - name: "claude-platform/*"
    provider: anthropic
    requestHeaders:
      set:
        anthropic-workspace-id: wrkspc_XXXXX
    params:
      awsRegion: us-west-2
      baseUrl: https://aws-external-anthropic.us-west-2.api.aws/v1
    auth:
      aws:
        serviceName: aws-external-anthropic
    transformation:
      model: llmRequest.model.stripPrefix("claude-platform/")

Use Claude on Azure AI Foundry

To use Claude models through Azure AI Foundry, configure the azure provider with azureResourceType: foundry and a Claude model name. Agentgateway automatically routes requests to the Anthropic-native endpoint and injects the required headers — no additional configuration is needed.

For setup instructions, see Use Claude models on Azure AI Foundry.

Connect to Claude Code

To route Claude Code CLI traffic through agentgateway, see the Claude Code integration guide.