Create a response

Creates a response using the OpenAI Responses API format. Supports streaming via SSE.

POST /v1/responses

Error

A valid request URL is required to generate request examples

200

{
  "id": "<string>",
  "background": true,
  "conversation": {},
  "created_at": 123,
  "error": {
    "code": "<string>",
    "message": "<string>"
  },
  "include": [
    "<string>"
  ],
  "incomplete_details": {
    "reason": "<string>"
  },
  "instructions": {},
  "max_output_tokens": 123,
  "max_tool_calls": 123,
  "metadata": {},
  "model": "<string>",
  "output": [
    {
      "id": "<string>",
      "type": "message",
      "status": "in_progress",
      "role": "assistant",
      "content": "<string>",
      "call_id": "<string>",
      "name": "<string>",
      "arguments": "<string>",
      "output": "<string>",
      "async": true,
      "action": {},
      "error": "<string>",
      "queries": [
        "<string>"
      ],
      "results": [
        {}
      ],
      "summary": [
        {
          "type": "summary_text",
          "text": "<string>"
        }
      ],
      "encrypted_content": "<string>"
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": "<string>",
  "prompt": {},
  "prompt_cache_key": "<string>",
  "reasoning": {
    "effort": "none",
    "generate_summary": "<string>",
    "summary": "auto",
    "max_tokens": 123
  },
  "safety_identifier": "<string>",
  "service_tier": "<string>",
  "status": "completed",
  "stop_reason": "<string>",
  "store": true,
  "temperature": 123,
  "text": {
    "format": {
      "type": "text",
      "name": "<string>",
      "schema": {},
      "strict": true
    },
    "verbosity": "low"
  },
  "top_logprobs": 123,
  "top_p": 123,
  "tool_choice": "none",
  "tools": [
    {
      "type": "function",
      "name": "<string>",
      "description": "<string>",
      "async": true,
      "cache_control": {
        "type": "ephemeral",
        "ttl": "<string>"
      },
      "parameters": {
        "type": "<string>",
        "description": "<string>",
        "required": [
          "<string>"
        ],
        "properties": {},
        "enum": [
          "<string>"
        ],
        "additionalProperties": true
      },
      "strict": true,
      "output_schema": {},
      "vector_store_ids": [
        "<string>"
      ],
      "filters": {},
      "max_num_results": 123,
      "ranking_options": {},
      "display_height": 123,
      "display_width": 123,
      "environment": "<string>",
      "enable_zoom": true,
      "search_context_size": "<string>",
      "user_location": {},
      "server_label": "<string>",
      "server_url": "<string>",
      "tunnel_id": "<string>",
      "allowed_tools": [
        "<string>"
      ],
      "authorization": "<string>",
      "connector_id": "<string>",
      "headers": {},
      "require_approval": {},
      "server_description": "<string>",
      "container": {},
      "background": "<string>",
      "input_fidelity": "<string>",
      "input_image_mask": {},
      "moderation": "<string>",
      "output_compression": 123,
      "output_format": "<string>",
      "partial_images": 123,
      "quality": "<string>",
      "size": "<string>",
      "format": {}
    }
  ],
  "truncation": "<string>",
  "usage": {
    "input_tokens": 123,
    "input_tokens_details": {
      "text_tokens": 123,
      "audio_tokens": 123,
      "image_tokens": 123,
      "cached_read_tokens": 123,
      "cached_write_tokens": 123
    },
    "output_tokens": 123,
    "output_tokens_details": {
      "text_tokens": 123,
      "accepted_prediction_tokens": 123,
      "audio_tokens": 123,
      "reasoning_tokens": 123,
      "rejected_prediction_tokens": 123,
      "citation_tokens": 123,
      "num_search_queries": 123
    },
    "total_tokens": 123,
    "cost": {
      "input_tokens_cost": 123,
      "output_tokens_cost": 123,
      "reasoning_tokens_cost": 123,
      "citation_tokens_cost": 123,
      "search_queries_cost": 123,
      "request_cost": 123,
      "total_cost": 123
    }
  },
  "tool_usage": {
    "web_search": {
      "num_requests": 123
    }
  },
  "extra_fields": {
    "request_type": "<string>",
    "provider": "anthropic",
    "model_requested": "<string>",
    "model_deployment": "<string>",
    "latency": 123,
    "chunk_index": 123,
    "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": 123,
      "threshold": 123,
      "similarity": 123
    }
  },
  "search_results": [
    {
      "title": "<string>",
      "url": "<string>",
      "date": "<string>",
      "last_updated": "<string>",
      "snippet": "<string>",
      "source": "<string>"
    }
  ],
  "videos": [
    {
      "url": "<string>",
      "thumbnail_url": "<string>",
      "thumbnail_width": 123,
      "thumbnail_height": 123,
      "duration": 123
    }
  ],
  "citations": [
    "<string>"
  ]
}

Authorizations

BearerAuthVirtualKeyAuthApiKeyAuth

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.

Body

application/json

model · string · required

Model in provider/model format

input · string object[] · required

Input - can be a string or array of messages

fallbacks · string[]

stream · boolean

background · boolean

conversation · string object

context_management · object

object[]

object

Show child attributes

include · string[]

instructions · string

max_output_tokens · integer

max_tool_calls · integer

metadata · object

parallel_tool_calls · boolean

previous_response_id · string

prompt_cache_key · string

reasoning · object

Show child attributes

safety_identifier · string

service_tier · string

stream_options · object

Show child attributes

store · boolean

temperature · number

text · object

Show child attributes

top_logprobs · integer

top_p · number

tool_choice · enum<string> object

Available options: none, auto, required

tools · object[]

Show child attributes

truncation · string

Response

200

application/json

Successful response

id · string

background · boolean

conversation · object

created_at · integer

error · object

Show child attributes

include · string[]

incomplete_details · object

Show child attributes

instructions · object

max_output_tokens · integer

max_tool_calls · integer

metadata · object

model · string

output · object[]

Show child attributes

parallel_tool_calls · boolean

previous_response_id · string

prompt · object

prompt_cache_key · string

reasoning · object

Show child attributes

safety_identifier · string

service_tier · string

status · enum<string>

Available options: completed, failed, in_progress, canceled, queued, incomplete

stop_reason · string

store · boolean

temperature · number

text · object

Show child attributes

top_logprobs · integer

top_p · number

tool_choice · enum<string> object

Available options: none, auto, required

tools · object[]

Show child attributes

truncation · string

usage · object

Show child attributes

tool_usage · object

Server-side tool call counts.

Show child attributes

extra_fields · object

Additional fields included in responses

Show child attributes

search_results · object[]

Show child attributes

videos · object[]

Show child attributes

citations · string[]