Qwen Messages

Call Qwen3.8 Max and Qwen3.8 Flash in the Anthropic Messages format with a BeatAPI key.

• One endpoint, POST /v1/messages, for every current Qwen model. Change model to switch.
• Streaming and tool use. Both models are priced flat across the whole 1,000,000-token window.
• Works with the Anthropic SDK: change the base URL and use a BeatAPI key. Send the anthropic-version header with every request.
• tool_choice is passed to the model, though not every model enforces it; thinking does not take effect. See the parameter reference below.

Opens this endpoint in the API Explorer. Enter your BeatAPI API key and send: the call is real and is billed to your own balance.

Models

Send one of these IDs as model. Each is a separate model; do not treat them as aliases of each other.

• Prices are the base tier, discount already applied. A long-context tier, cached-input rates and cache writes are not in this table; see the price table.
• — means the catalogue does not publish the number.

Quick start

Install the @anthropic-ai/sdk or anthropic package on your server, keep the key in BEATAPI_API_KEY, and never put it in browser code. The SDK sends the anthropic-version header for you. These are request examples, not recorded model outputs.

Read the answer from the text blocks of content, then check stop_reason and usage. An HTTP 200 alone does not prove the answer satisfies your task: validate it in your application. Text requests return directly; do not poll /v1/tasks for them.

curl --request POST \
  --url https://direct.beatapi.io/v1/messages \
  --header "x-api-key: $BEATAPI_API_KEY" \
  --header 'anthropic-version: 2023-06-01' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "qwen3.8-max",
  "max_tokens": 2000,
  "messages": [
    {
      "role": "user",
      "content": "Design a resilient webhook retry strategy for a payments API."
    }
  ]
}'

Endpoint and authentication

POST https://direct.beatapi.io/v1/messages

Send the anthropic-version header (for example 2023-06-01) with every request; the Anthropic SDK adds it automatically. For authentication, x-api-key and Authorization: Bearer <BEATAPI_API_KEY> both work.

Request parameters

The request uses the Anthropic Messages shape. The fields below take effect; the last two are accepted by the SDK but do not change the result. A field that is not listed on this page is not guaranteed to have any effect.

Response

A non-streaming call returns one JSON object. This is an abbreviated example.

{
  "id": "msg_example",
  "type": "message",
  "role": "assistant",
  "model": "qwen3.8-max",
  "content": [
    {
      "type": "text",
      "text": "Retry with exponential backoff and jitter, and make every handler idempotent."
    }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 19,
    "output_tokens": 16
  }
}

Response fields

Streaming

Set "stream": true. The stream starts with message_start and ends with message_stop; the blocks in between arrive as content_block_start, content_block_delta and content_block_stop events, and message_delta carries the stop_reason.

• The response is text/event-stream; without streaming it is application/json.
• Text arrives in text_delta events. A reasoning model sends a thinking block with thinking_delta events before the text block. Tool arguments arrive in input_json_delta events.
• A failure before the model is called is returned as a normal JSON error with an HTTP status, not as a stream event.
• Set explicit timeouts and reconnect a streamed response safely.

event: message_start
data: {"type":"message_start","message":{"id":"msg_example","type":"message","role":"assistant","content":[],"usage":{"input_tokens":19,"output_tokens":1}}}
event: content_block_start
data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}
event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Retry"}}
event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" with backoff"}}
event: content_block_stop
data: {"type":"content_block_stop","index":0}
event: message_delta
data: {"type":"message_delta","delta":{"stop_reason":"end_turn"},"usage":{"output_tokens":16}}
event: message_stop
data: {"type":"message_stop"}

Errors

HTTP errors at a glance

Authentication, routing, rate-limit and unknown-model failures are answered before the model is called, in the BeatAPI envelope: error.code, error.message, retryable, request_id. Every other failure keeps the Anthropic shape {"type": "error", "error": {"type", "message"}}: the code is in error.type and the request id ends message. See Errors.

Full code table and retry policy: Errors.

Notes

• Qwen models also answer on Chat Completions and OpenAI Responses.
• Cached input is priced separately from fresh input. A repeated prompt prefix is billed at the cache rate automatically; there is no cache API to call, so check the cached-input count in usage.
• Send anthropic-version with every request. Do not rely on thinking: it does not take effect.
• Keep API keys on trusted servers, log the response request ID, and retry only 429, 500 and 503.