Try Bifrost Enterprise free for 14 days. Explore now
curl --request POST \
--url http://localhost:8080/openai/v1/responses \
--header 'Content-Type: application/json' \
--data '
{
"model": "gpt-4",
"input": "<string>",
"stream": true,
"instructions": "<string>",
"max_output_tokens": 123,
"metadata": {},
"parallel_tool_calls": true,
"previous_response_id": "<string>",
"reasoning": {
"effort": "none",
"generate_summary": "auto",
"summary": "auto",
"max_tokens": 123
},
"store": true,
"temperature": 1,
"text": {
"format": {
"type": "text",
"json_schema": {
"name": "<string>",
"schema": {},
"strict": true
}
}
},
"tool_choice": "none",
"tools": [
{
"type": "function",
"name": "<string>",
"description": "<string>",
"cache_control": {
"type": "ephemeral",
"ttl": "<string>"
},
"parameters": {
"type": "<string>",
"description": "<string>",
"required": [
"<string>"
],
"properties": {},
"enum": [
"<string>"
],
"additionalProperties": true
},
"strict": true,
"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>",
"allowed_tools": {},
"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": {}
}
],
"top_p": 123,
"truncation": "auto",
"user": "<string>",
"fallbacks": [
"<string>"
]
}
'{
"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": {},
"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>",
"cache_control": {
"type": "ephemeral",
"ttl": "<string>"
},
"parameters": {
"type": "<string>",
"description": "<string>",
"required": [
"<string>"
],
"properties": {},
"enum": [
"<string>"
],
"additionalProperties": true
},
"strict": true,
"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>",
"allowed_tools": {},
"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
}
},
"extra_fields": {
"request_type": "<string>",
"provider": "openai",
"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>"
]
}Creates a response using OpenAI Responses API 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 status will not be completed. When completed, the full response with output_text will be returned. See Async Inference for details.
Note: This endpoint also works without the /v1 prefix (e.g., /openai/responses).
curl --request POST \
--url http://localhost:8080/openai/v1/responses \
--header 'Content-Type: application/json' \
--data '
{
"model": "gpt-4",
"input": "<string>",
"stream": true,
"instructions": "<string>",
"max_output_tokens": 123,
"metadata": {},
"parallel_tool_calls": true,
"previous_response_id": "<string>",
"reasoning": {
"effort": "none",
"generate_summary": "auto",
"summary": "auto",
"max_tokens": 123
},
"store": true,
"temperature": 1,
"text": {
"format": {
"type": "text",
"json_schema": {
"name": "<string>",
"schema": {},
"strict": true
}
}
},
"tool_choice": "none",
"tools": [
{
"type": "function",
"name": "<string>",
"description": "<string>",
"cache_control": {
"type": "ephemeral",
"ttl": "<string>"
},
"parameters": {
"type": "<string>",
"description": "<string>",
"required": [
"<string>"
],
"properties": {},
"enum": [
"<string>"
],
"additionalProperties": true
},
"strict": true,
"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>",
"allowed_tools": {},
"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": {}
}
],
"top_p": 123,
"truncation": "auto",
"user": "<string>",
"fallbacks": [
"<string>"
]
}
'{
"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": {},
"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>",
"cache_control": {
"type": "ephemeral",
"ttl": "<string>"
},
"parameters": {
"type": "<string>",
"description": "<string>",
"required": [
"<string>"
],
"properties": {},
"enum": [
"<string>"
],
"additionalProperties": true
},
"strict": true,
"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>",
"allowed_tools": {},
"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
}
},
"extra_fields": {
"request_type": "<string>",
"provider": "openai",
"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>"
]
}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.
Model identifier
"gpt-4"
Input - can be a string or array of messages
System instructions for the model
Show child attributes
0 <= x <= 2Show child attributes
none, auto, required Show child attributes
auto, disabled Successful response
Show child attributes
Show child attributes
Show child attributes
Show child attributes
completed, failed, in_progress, canceled, queued, incomplete Show child attributes
none, auto, required Show child attributes
Show child attributes
Additional fields included in responses
Show child attributes
Show child attributes
Show child attributes
Was this page helpful?