Anthropic Messages

POST /v1/messages

Use the model name shown on the Pricing page.

Authentication

x-api-key: OMROUTER_API_KEY
anthropic-version: 2023-06-01
content-type: application/json

Request body

Field	Type	Required	Description
model	string	Yes	Model name shown on the Pricing page.
messages	array	Yes	Conversation turns.
max_tokens	integer	Yes	Maximum output tokens for the Messages request.
system	string or array	No	System instructions.
stream	boolean	No	Return Anthropic-style streaming events.
temperature	number	No	Sampling control where supported.
tools	array	No	Tool definitions where supported.
tool_choice	object	No	Tool selection control where supported.
thinking	object	No	Thinking configuration where supported.

Example

curl --silent --show-error \
  'https://omrouter.com/v1/messages' \
  --header "x-api-key: $OMROUTER_API_KEY" \
  --header 'anthropic-version: 2023-06-01' \
  --header 'content-type: application/json' \
  --data "{
    \"model\": \"$OMROUTER_MODEL_ID\",
    \"max_tokens\": 256,
    \"messages\": [
      {\"role\": \"user\", \"content\": \"Reply with one short sentence.\"}
    ]
  }"

Response

{
  "id": "msg_...",
  "type": "message",
  "role": "assistant",
  "model": "model-id",
  "content": [
    {"type": "text", "text": "..."}
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0
  }
}

See Anthropic SDKs for Python and JavaScript configuration.

Optional features

Basic messages, streaming, and tools can be tested directly. Anthropic beta features, prompt caching, and thinking depend on the selected model. If the API reports an unsupported parameter, remove that optional field and try again.