Create chat completion

OpenAI-compatible Chat Completions, including streaming and the signed receipt.

POST https://mifr-gateway-production.up.railway.app/v1/chat/completions

cURL

curl https://mifr-gateway-production.up.railway.app/v1/chat/completions \
  -H "Authorization: Bearer $MIFR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-4b",
    "messages": [{"role": "user", "content": "Reply with the single word pong."}]
  }'

200

{
  "id": "chatcmpl-…",
  "object": "chat.completion",
  "model": "qwen3-4b",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "pong" },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 1,
    "total_tokens": 13
  },
  "mifr_receipt": {
    "trust_level": "hardware",
    "model_id": "qwen3-4b"
  }
}

This is the OpenAI-compatible Chat Completions endpoint, for both stream and non-stream calls. A non-stream 200 is a chat.completion with usage and mifr_receipt. Stream is SSE (text/event-stream): a role chunk, content deltas, keepalives every 10 seconds (: keepalive), a stop chunk, then data: [DONE].

The JSON model field echoes the request. The alias actually served is x-mifr-model / mifr_receipt.model_id.

Authorization · string · required

Bearer product key. Format: Bearer sk-mifr_…. See Authentication.

model · string · required

Catalog alias or Hugging Face id. An empty value is 400. An unknown name is 404 model_not_found. Default alias: qwen3-4b.

messages · object[] · required

Non-empty. Each item needs role. Max 100 messages, 256 KiB total content chars.

Show message fields

role · string · required

Message role (user, assistant, system, and so on).

content · string | object[] · required

A string, or parts {"type":"text"|"input_text", "text":"…"}. Other part types (for example image_url) return 400.

max_tokens · number · default: "512"

Integer. Fractional values are rejected. Qwen3 is a thinking model, so a tiny cap often fills with <think>… and never reaches a visible answer.

max_completion_tokens · number

Alias for max_tokens. max_tokens wins if both are set.

temperature · number · default: "0.7"

Number. Bools and string numbers are rejected.

stream · boolean · default: "false"

If true, respond as SSE. The receipt and x_mifr_* verdicts are on the final chunk, not on the SSE HTTP head.

provider · string

Pin one Mac: exact provider id, or a unique prefix of at least 8 characters. A pin does not hop or hedge. If that Mac is offline or below the floor, the call returns 503 provider_unavailable.

provider_key_id · string

Alias for provider.

stream_options · object

Extra keys are ignored. include_usage still appears on the stop chunk.

Response

id · string

Completion id.

object · string

chat.completion (non-stream) or chat.completion.chunk (stream).

model · string

Echo of the request model field.

choices · object[]

Standard OpenAI choices. A stream sends a role chunk, then content deltas, then a stop chunk.

usage · object

Token counts from the verified receipt. Present on non-stream 200 and on the terminal SSE chunk.

mifr_receipt · object

Signed, request-bound receipt. This is the proof; HTTP x-mifr-* headers are the gateway’s report of the same facts.

Failure after the first streamed token puts the same error object in data: and omits [DONE]. Do not splice a retry onto those bytes. If the caller hangs up, the gateway aborts the seal (aborted) and sends no body.

See Errors and headers for the full mifr_action table and verdict header list.

cURL

curl https://mifr-gateway-production.up.railway.app/v1/chat/completions \
  -H "Authorization: Bearer $MIFR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-4b",
    "messages": [{"role": "user", "content": "Reply with the single word pong."}]
  }'

200

{
  "id": "chatcmpl-…",
  "object": "chat.completion",
  "model": "qwen3-4b",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "pong" },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 1,
    "total_tokens": 13
  },
  "mifr_receipt": {
    "trust_level": "hardware",
    "model_id": "qwen3-4b"
  }
}