Create chat completion (OpenAI format)
Creates a chat completion using OpenAI-compatible format. Supports streaming via SSE.
Async inference: Send x-bf-async: true to submit the request as a background job and receive a job ID immediately. Poll with x-bf-async-id: <job-id> to retrieve the result. When the job is still processing, the response will have an empty choices array. When completed, choices will contain the full result. See Async Inference for details.
Note: This endpoint also works without the /v1 prefix (e.g., /openai/chat/completions).
Bearer token authentication. Use your MPilot virtual-key JWT or admin JWT.
Virtual keys (prefixed with sk-bf-) can also be passed here.
In: header
Header Parameters
Set to true to submit this request as an async job. Returns immediately with a job ID. Not compatible with streaming.
"true"Poll for results of a previously submitted async job by providing the job ID returned from the initial async request.
Override the default result TTL in seconds. Results expire after this duration from completion time.
3600Model identifier (e.g., gpt-4, gpt-3.5-turbo)
List of messages in the conversation
Whether to stream the response
Maximum tokens to generate (legacy, use max_completion_tokens)
Maximum tokens to generate
0 <= value <= 2-2 <= value <= 2-2 <= value <= 2Empty Object
Format for the response
Empty Object
OpenAI reasoning effort level
"none" | "minimal" | "low" | "medium" | "high" | "xhigh"Fallback models
Response Body
curl -X POST "https://loading/{AI_GATEWAY_URL}/openai/v1/chat/completions" \ -H "x-bf-async: true" \ -H "x-bf-async-id: string" \ -H "x-bf-async-job-result-ttl: 3600" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-4", "messages": [ { "role": "system" } ] }'{
"id": "string",
"choices": [
{
"index": 0,
"finish_reason": "string",
"log_probs": {
"content": [
{
"bytes": [
0
],
"logprob": 0,
"token": "string",
"top_logprobs": [
{
"bytes": [
0
],
"logprob": 0,
"token": "string"
}
]
}
],
"refusal": [
{
"bytes": [
0
],
"logprob": 0,
"token": "string"
}
],
"text_offset": [
0
],
"token_logprobs": [
0
],
"tokens": [
"string"
],
"top_logprobs": [
{
"property1": 0,
"property2": 0
}
]
},
"text": "string",
"message": {
"role": "assistant",
"name": "string",
"content": "string",
"tool_call_id": "string",
"refusal": "string",
"audio": {
"id": "string",
"data": "string",
"expires_at": 0,
"transcript": "string"
},
"reasoning": "string",
"reasoning_details": [
{
"id": "string",
"index": 0,
"type": "reasoning.summary",
"summary": "string",
"text": "string",
"signature": "string",
"data": "string"
}
],
"annotations": [
{
"type": "string",
"url_citation": {
"start_index": 0,
"end_index": 0,
"title": "string",
"url": "string",
"sources": {},
"type": "string"
}
}
],
"tool_calls": [
{
"index": 0,
"type": "string",
"id": "string",
"function": {
"name": "string",
"arguments": "string"
}
}
]
},
"delta": {
"role": "string",
"content": "string",
"refusal": "string",
"audio": {
"id": "string",
"data": "string",
"expires_at": 0,
"transcript": "string"
},
"reasoning": "string",
"reasoning_details": [
{
"id": "string",
"index": 0,
"type": "reasoning.summary",
"summary": "string",
"text": "string",
"signature": "string",
"data": "string"
}
],
"tool_calls": [
{
"index": 0,
"type": "string",
"id": "string",
"function": {
"name": "string",
"arguments": "string"
}
}
]
}
}
],
"created": 0,
"model": "string",
"object": "string",
"service_tier": "string",
"system_fingerprint": "string",
"usage": {
"prompt_tokens": 0,
"prompt_tokens_details": {
"text_tokens": 0,
"audio_tokens": 0,
"image_tokens": 0,
"cached_read_tokens": 0,
"cached_write_tokens": 0
},
"completion_tokens": 0,
"completion_tokens_details": {
"text_tokens": 0,
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"citation_tokens": 0,
"num_search_queries": 0,
"reasoning_tokens": 0,
"image_tokens": 0,
"rejected_prediction_tokens": 0
},
"total_tokens": 0,
"cost": {
"input_tokens_cost": 0,
"output_tokens_cost": 0,
"reasoning_tokens_cost": 0,
"citation_tokens_cost": 0,
"search_queries_cost": 0,
"request_cost": 0,
"total_cost": 0
}
},
"extra_fields": {
"request_type": "string",
"provider": "openai",
"model_requested": "string",
"model_deployment": "string",
"latency": 0,
"chunk_index": 0,
"raw_request": {},
"raw_response": {},
"cache_debug": {
"cache_hit": true,
"cache_id": "string",
"hit_type": "string",
"requested_provider": "string",
"requested_model": "string",
"provider_used": "string",
"model_used": "string",
"input_tokens": 0,
"threshold": 0,
"similarity": 0
}
},
"search_results": [
{
"title": "string",
"url": "string",
"date": "string",
"last_updated": "string",
"snippet": "string",
"source": "string"
}
],
"videos": [
{
"url": "string",
"thumbnail_url": "string",
"thumbnail_width": 0,
"thumbnail_height": 0,
"duration": 0
}
],
"citations": [
"string"
]
}{
"event_id": "string",
"type": "string",
"is_bifrost_error": true,
"status_code": 0,
"error": {
"type": "string",
"code": "string",
"message": "string",
"param": "string",
"event_id": "string"
},
"extra_fields": {
"provider": "openai",
"model_requested": "string",
"request_type": "string"
}
}{
"event_id": "string",
"type": "string",
"is_bifrost_error": true,
"status_code": 0,
"error": {
"type": "string",
"code": "string",
"message": "string",
"param": "string",
"event_id": "string"
},
"extra_fields": {
"provider": "openai",
"model_requested": "string",
"request_type": "string"
}
}