Anthropic Messages API

The Anthropic Messages API, for Claude Code and Anthropic SDKs. Base URL https://api.openscale.so/anthropic.

Endpoint

• Create a message: POST https://api.openscale.so/anthropic/v1/messages

Create a message

POST https://api.openscale.so/anthropic/v1/messages

The Anthropic Messages API: system prompts, multi-turn messages with text, image, tool_use and tool_result blocks, client tools and tool_choice, extended thinking, stop_sequences and streaming with the standard event sequence. Any claude-* model name runs DeepSeek V4.1 Flash, and the reply echoes the name you sent. Thinking (thinking.type enabled or adaptive, or output_config.effort) turns reasoning on; it comes back as thinking blocks. Anthropic server tools are ignored. Usage reports cache_read_input_tokens for prompt tokens billed at the cached rate. Errors use the Anthropic shape.

Request body

Example request

curl https://api.openscale.so/anthropic/v1/messages \
  -H "x-api-key: $OPENSCALE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-sonnet-4-5",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello from OpenScale"
    }
  ]
}'

Response

200: The message, or an SSE stream when stream is true: message_start, content_block_start, content_block_delta, content_block_stop, message_delta and message_stop.

{
  "id": "msg_example",
  "type": "message",
  "role": "assistant",
  "model": "claude-sonnet-4-5",
  "content": [
    {
      "type": "text",
      "text": "Hello!"
    }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 9,
    "cache_read_input_tokens": 0,
    "output_tokens": 3
  }
}

Errors

More of the API reference

• API reference: base URLs, authentication and a first request.
• Chat Completions: POST /v1/chat/completions: the OpenAI Chat Completions format, streamed or not, with reasoning and tools.
• Responses: POST /v1/responses: the OpenAI Responses format with stored state, background runs and enforced tool rules.
• Conversations: Keep the turns of a Responses conversation on our side and continue it by id.
• Prompts: Save instructions, messages and settings once, then use them by id in the Responses API.
• Models and pricing: Model ids, prices per 1M tokens, context windows, output limits, versions and the live catalog endpoint.
• Batch: Upload a JSONL file of chat completions, create a batch and collect the results when it finishes.
• Errors: The error shape, every status code and code, and which ones to retry.
• Rate limits: Requests and tokens per minute, how a 429 tells you when to retry, and how to get more.
• Data retention: What is stored, for how long, how to delete it, and zero data retention.
• Interactive reference: try every endpoint in the browser.
• OpenAPI document: the whole API as OpenAPI 3.1.