Mixedbread

Create a Response

Create an OpenAI-compatible response with text input or client-executed function tools.

POST
/v1/responses

Authorization

ApiKeyAuth
headerAuthorizationBearer <token>

Api key to access Mixedbreads API

Request Body

application/json
  1. body

OpenAI-compatible response parameters

model?Model
Default"toast-1"
input*string|array<||||||||>
instructions?string|null
tools?array<||||||||||||>
tool_choice?|||||||||||
Default"auto"
store?Store
Defaulttrue
previous_response_id?string|null
context_management?|null
stream?Stream
Defaultfalse
stream_options?|null
temperature?|null
top_p?|null
max_output_tokens?|null
max_tool_calls?|null
parallel_tool_calls?Parallel Tool Calls
Defaulttrue
metadata?|null
include?array<string>|null
text?|null
background?Background
Defaultfalse
truncation?Truncation
Default"disabled"
Value in"auto""disabled"
reasoning?|null
service_tier?|null
safety_identifier?|null
prompt_cache_key?string|null
user?string|null
client_metadata?|null

Response Body

The generated response, or a semantic server-sent event stream

application/json
  1. response

A completed or in-progress OpenAI-compatible Response object.

id*Id
object?Object
Default"response"
created_at*Created At
status*Status
Value in"completed""failed""in_progress""cancelled""queued""incomplete"
completed_at?number|null
error?|null
incomplete_details?|null
instructions?string|null
model?Model
Default"toast-1"
output?array<|||||>
parallel_tool_calls?Parallel Tool Calls
Defaulttrue
temperature?number|null
tool_choice?||
Default"auto"
tools?array<||>
top_p?number|null
background?Background
Defaultfalse
max_output_tokens?integer|null
max_tool_calls?integer|null
previous_response_id?string|null
reasoning?|null
service_tier?Service Tier
Default"default"
Value in"auto""default""flex""scale""priority"
text?|null
truncation?Truncation
Default"disabled"
Value in"auto""disabled"
usage?|null
metadata?|null
safety_identifier?string|null
prompt_cache_key?string|null
user?string|null
hosted_tool_calls?array<|||||||||>
hosted_tools?array<|||||||||>
tool_tickets?array<>
context_management?|null
title?string|null
Example Request
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mixedbread.com/v1",
    api_key="YOUR_API_KEY",
)

response = client.responses.create(
    model="toast-1",
    input="What is a search agent?",
)

print(response.output_text)
Example Response
{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1786622400,
  "status": "completed",
  "completed_at": 1786622401,
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "model": "toast-1",
  "output": [
    {
      "type": "message",
      "id": "msg_abc123",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "annotations": [],
          "text": "A search agent plans queries, gathers evidence with tools, and synthesizes an answer.",
          "logprobs": []
        }
      ]
    }
  ],
  "parallel_tool_calls": true,
  "temperature": null,
  "tool_choice": "auto",
  "tools": [],
  "top_p": null,
  "background": false,
  "max_output_tokens": null,
  "previous_response_id": null,
  "reasoning": null,
  "service_tier": "default",
  "text": null,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 15,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 19,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 34
  },
  "metadata": null,
  "safety_identifier": null,
  "prompt_cache_key": null,
  "user": null,
  "title": "What is a search agent?"
}

Stored response lifecycle

Responses created with store: true can also use the OpenAI-compatible retrieve, delete, and input-items endpoints. These operations use the same REST paths and OpenAI SDK method names. Use the Mixedbread base URL and API key shown in the examples above.

OperationREST endpointPythonTypeScriptSupported query parameters
Retrieve a responseGET /v1/responses/{response_id}client.responses.retrieve(response_id)client.responses.retrieve(responseId)stream, starting_after
Delete a responseDELETE /v1/responses/{response_id}client.responses.delete(response_id)client.responses.delete(responseId)None
List input itemsGET /v1/responses/{response_id}/input_itemsclient.responses.input_items.list(response_id)client.responses.inputItems.list(responseId)limit, order, after

Mixedbread supports the OpenAI lifecycle shape for text messages and client-executed function items. OpenAI options or item types not documented on this page are not supported. Deleting a stored response also deletes its persisted conversation chain.