Messages · bInference Docs

Anthropic's format, used by Claude Code and the Anthropic SDKs. It works with every listed model, not only Claude.

max_tokens is required, as in Anthropic's own API. A busy model answers 529 overloaded_error, so Claude Code moves to its fallback model. Messages answers carry no cost: find each call's charge on your Calls page.

Send your key as Authorization: Bearer binf_... or x-api-key.

Request body

The fields most calls use. Every other field of the Anthropic format is passed on as sent.

modelstringRequired
A model id from GET /models. Claude clients' own names work too: claude-sonnet-5-5, dated names and the [1m] suffix map to the listed model.
messagesobject[]Required
The conversation so far, alternating user and assistant.
max_tokensintegerRequired
The longest answer, in tokens. The call reserves this much output while it runs.
systemstring | object[]
The system prompt.
streamboolean
Send the answer as it is written, as server-sent events. Recommended for anything longer than a sentence: streams may run 30 minutes, other calls 13.
temperaturenumber
Randomness, 0 to 2. Lower is more predictable.
toolsobject[]
Functions the model may call, in the format's own shape. Your code runs them and sends the results back. Web search and web fetch are also served.
thinkingobject
{ "type": "enabled", "budget_tokens": 2048 } for extended thinking. Thinking is billed as output.

Headers

anthropic-versionstring
Passed on as sent. The Anthropic SDKs set it.
anthropic-betastring
Passed on as sent, for beta features.

Response

idstring
The message's id.
contentobject[]
Blocks: text, thinking and tool_use.
stop_reasonstring
Why the answer ended.
usageobject
input_tokens and output_tokens. The Messages format carries no cost: find each call's charge on your Calls page within a minute.

Response headers

x-binference-call-idstring
This call's id on your Calls page. Quote it when you contact us.
x-generation-idstring
The model provider's id for the answer.
retry-afterinteger
On a 429 or 503: whole seconds to wait before sending again.
retry-after-msinteger
The same wait in milliseconds. The OpenAI and Anthropic SDKs read it.

Request

curl https://binference.io/api/v1/messages \  -H "Authorization: Bearer $BINF_API_KEY" \  -H "anthropic-version: 2023-06-01" \  -H "Content-Type: application/json" \  -d '{    "model": "anthropic/claude-sonnet-5.5",    "max_tokens": 256,    "system": "You are a concise trading assistant.",    "messages": [      {        "role": "user",        "content": "Summarize the last 24 hours of trades in one line."      }    ]  }'

Response

{  "id": "msg_01XFDUDYJgAACzvnptvVoYEL",  "type": "message",  "role": "assistant",  "model": "anthropic/claude-sonnet-5.5",  "content": [    {      "type": "text",      "text": "12 trades today: 9 wins, net +3.4 BNB, biggest move on $NOVA."    }  ],  "stop_reason": "end_turn",  "usage": {    "input_tokens": 27,    "output_tokens": 22  }}

Streamed, with stream: true

event: message_startdata: {"type":"message_start","message":{"id":"msg_01XFDUDYJgAACzvnptvVoYEL","role":"assistant","usage":{"input_tokens":27,"output_tokens":1}}}event: content_block_deltadata: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"12 trades today"}}event: message_deltadata: {"type":"message_delta","delta":{"stop_reason":"end_turn"},"usage":{"output_tokens":22}}event: message_stopdata: {"type":"message_stop"}