Create async chat completion

Submits a chat completion request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result. Streaming is not supported for async requests.

POST /v1/async/chat/completions

Error

A valid request URL is required to generate request examples

202

{
  "id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "expires_at": "2023-11-07T05:31:56Z",
  "completed_at": "2023-11-07T05:31:56Z",
  "status_code": 123,
  "result": "<unknown>",
  "error": {
    "event_id": "<string>",
    "type": "<string>",
    "is_bifrost_error": true,
    "status_code": 123,
    "error": {
      "type": "<string>",
      "code": "<string>",
      "message": "<string>",
      "param": "<string>",
      "event_id": "<string>"
    },
    "extra_fields": {
      "model_requested": "<string>",
      "request_type": "<string>"
    }
  }
}

Authorizations

BearerAuthBasicAuthVirtualKeyAuthApiKeyAuth

Authorization · string · header · required

Bearer token authentication. Use your provider API key or Bifrost authentication token. Virtual keys (prefixed with sk-bf-) can also be passed here.

Headers

x-bf-async-job-result-ttl · integer · default: 3600

Time-to-live in seconds for the job result after completion. Defaults to 3600 (1 hour). After expiry, the job result is automatically cleaned up.

Body

application/json

model · string · required

Model in provider/model format (e.g., openai/gpt-4)

Example:

"openai/gpt-4"

messages · object[] · required

List of messages in the conversation

Show child attributes

fallbacks · string[]

Fallback models in provider/model format

stream · boolean

Whether to stream the response

frequency_penalty · number

Required range: -2 <= x <= 2

logit_bias · object

Show child attributes

logprobs · boolean

max_completion_tokens · integer

metadata · object

modalities · string[]

parallel_tool_calls · boolean

presence_penalty · number

Required range: -2 <= x <= 2

prompt_cache_key · string

reasoning · object

Show child attributes

response_format · object

Format for the response

safety_identifier · string

service_tier · string

stream_options · object

Show child attributes

store · boolean

temperature · number

Required range: 0 <= x <= 2

tool_choice · enum<string> object

Available options: none, auto, required

tools · object[]

Show child attributes

seed · integer

Deterministic sampling seed

top_p · number

Nucleus sampling parameter

Required range: 0 <= x <= 1

top_logprobs · integer

Number of most likely tokens to return at each position

Required range: 0 <= x <= 20

stop · string string[]

Up to 4 sequences where the API will stop generating tokens

prediction · object

Predicted output content for the model to reference (OpenAI only). Can reduce latency.

Show child attributes

prompt_cache_retention · enum<string>

Prompt cache retention policy

Available options: in-memory, 24h

web_search_options · object

Web search options for chat completions (OpenAI only)

Show child attributes

truncation · string

user · string

verbosity · enum<string>

Available options: low, medium, high

Response

202

application/json

Job accepted for processing

Response returned when creating or polling an async job

id · string · required

Unique identifier for the async job

status · enum<string> · required

The status of an async job

Available options: pending, processing, completed, failed

created_at · string<date-time> · required

When the job was created

expires_at · string<date-time>

When the job result expires and will be cleaned up

completed_at · string<date-time>

When the job completed (successfully or with failure)

status_code · integer

HTTP status code of the completed operation

result · any

The result of the completed operation (shape depends on the request type)

error · object

Error response from Bifrost

Show child attributes