Azure Integration
Create chat completion (Azure OpenAI)
Creates a chat completion using Azure OpenAI deployment.
AuthorizationBearer <token>
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
Path Parameters
deployment-idstring
Azure deployment ID
Query Parameters
api-version?string
Azure API version
modelstring
Model identifier (e.g., gpt-4, gpt-3.5-turbo)
messagesarray<OpenAIMessage>
List of messages in the conversation
stream?boolean
Whether to stream the response
max_tokens?integer
Maximum tokens to generate (legacy, use max_completion_tokens)
max_completion_tokens?integer
Maximum tokens to generate
temperature?number
Range
0 <= value <= 2top_p?number
frequency_penalty?number
Range
-2 <= value <= 2presence_penalty?number
Range
-2 <= value <= 2logit_bias?object
Empty Object
logprobs?boolean
top_logprobs?integer
n?integer
stop?string | array<string>
seed?integer
user?string
tools?array<object>
tool_choice?string | object
parallel_tool_calls?boolean
response_format?object
Format for the response
Empty Object
reasoning_effort?string
OpenAI reasoning effort level
Value in
"none" | "minimal" | "low" | "medium" | "high" | "xhigh"service_tier?string
stream_options?object
fallbacks?array<string>
Fallback models
Response Body
curl -X POST "https://loading/{AI_GATEWAY_URL}/openai/openai/deployments/string/chat/completions?api-version=string" \ -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"
}
}