Responses · bInference Docs

The newer OpenAI format, with input and instructions in place of messages. Codex uses it.

It is stateless here: nothing is stored, so previous_response_id and saved prompts aren't served. Send the conversation as input items each time.

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

Request body

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

modelstringRequired
A model id from GET /models, such as anthropic/claude-sonnet-5.5. Add :online for web search, or :nitro, :floor or :exacto to steer which provider runs it.
inputstring | object[]Required
A prompt, or the conversation as input items.
instructionsstring
The system prompt.
max_output_tokensinteger
The longest answer, in tokens. Set it: the call reserves its longest possible answer while it runs.
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.
max_tool_callsinteger
The most tool steps in one call. Web search loops reserve for every step, so a lower number reserves less.
reasoningobject
For reasoning models: { "effort": "low" | "medium" | "high" }.
modelsstring[]
Fallback models, tried in order when the first is busy or down. The reserve covers the dearest of them.

Response

idstring
The response's id.
outputobject[]
Output items: messages, reasoning and tool calls. output_text joins the text.
usageobject
input_tokens, output_tokens and cost: what this call is charged, in dollars.

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/responses \  -H "Authorization: Bearer $BINF_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "openai/gpt-6.1-sol",    "instructions": "You are a concise trading assistant.",    "input": "Summarize the last 24 hours of trades in one line.",    "max_output_tokens": 256  }'

Response

{  "id": "resp_7Yq2c1",  "object": "response",  "status": "completed",  "model": "openai/gpt-6.1-sol",  "output": [    {      "type": "message",      "role": "assistant",      "content": [        {          "type": "output_text",          "text": "12 trades today: 9 wins, net +3.4 BNB, biggest move on $NOVA."        }      ]    }  ],  "usage": {    "input_tokens": 29,    "output_tokens": 21,    "total_tokens": 50,    "cost": 0.000322  }}

Streamed, with stream: true

event: response.createddata: {"type":"response.created","response":{"id":"resp_7Yq2c1","status":"in_progress"}}event: response.output_text.deltadata: {"type":"response.output_text.delta","delta":"12 trades today"}event: response.completeddata: {"type":"response.completed","response":{"id":"resp_7Yq2c1","status":"completed","usage":{"input_tokens":29,"output_tokens":21,"total_tokens":50,"cost":0.000322}}}