Responses

Create response

Authorization

bearerAuth

AuthorizationBearer <token>

API key in format: eur_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

In: header

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

models?array<string>

Fallback model list (EUrouter extension)

rule_id?string

Routing rule ID to apply (EUrouter extension)

Match

^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$

Formatuuid

rule_name?string

Routing rule name to apply (EUrouter extension)

provider?

Provider routing preferences (EUrouter extension)

model?string

Model identifier (e.g., "gpt-4o")

input*|array<|||>

The input to generate a response for

instructions?||

System-level instructions for the model

previous_response_id?||

ID of previous response for conversation continuity

stream?||

Enable streaming responses

stream_options?||

Options for streaming responses

max_output_tokens?||

Maximum tokens to generate

temperature?||

Sampling temperature (0-2)

top_p?||

Nucleus sampling probability (0-1)

tools?array<|||||>

Available tools for the model

tool_choice?||||

Tool calling behavior

parallel_tool_calls?boolean

Allow parallel tool calls

truncation?string

Context truncation strategy

Value in"auto" | "disabled"

metadata?

Custom metadata

user?||

End-user identifier for abuse detection

store?||

Whether to store the response

reasoning?||

Reasoning parameters (for reasoning models)

reasoning_effort?||

OpenAI-compatible shorthand for reasoning.effort

text?

Text format specification

background?boolean

Whether to run the response in the background

conversation?unknown

OpenAI conversation continuation configuration

context_management?

OpenAI context management configuration

frequency_penalty?||

Frequency penalty

image_config?unknown

Image output configuration

include?array<>

Additional output data to include

max_tool_calls?number

Maximum number of tool calls allowed

modalities?array<string>

Requested output modalities

plugins?array<>

Optional plugins (e.g. { id: "response-healing", enabled?: boolean })

presence_penalty?||

Presence penalty

prompt?

OpenAI prompt template reference

prompt_cache_key?||

Prompt cache key

prompt_cache_retention?||

Prompt cache retention policy

route?unknown

Routing descriptor

safety_identifier?||

Stable safety identifier

service_tier?string

Service tier for the request

Value in"auto" | "default" | "flex" | "scale" | "priority"

top_k?integer

Top-k sampling parameter

Range-9007199254740991 <= value <= 9007199254740991

top_logprobs?||

Number of top logprobs to return

trace?

Trace context for Broadcast observability

session_id?string

Session identifier for grouping related requests

Lengthlength <= 128

[key: string]?unknown

Response Body

`application/json`

curl -X POST "https://api.eurouter.ai/api/v1/responses" \  -H "Content-Type: application/json" \  -d '{    "model": "mistral-large-3",    "input": "Explain EU data residency in one sentence."  }'

{
  "id": "string",
  "object": "response",
  "created_at": 0,
  "status": "queued",
  "model": "string",
  "provider": "string",
  "output": [
    {
      "type": "message",
      "id": "string",
      "role": "assistant",
      "status": "in_progress",
      "content": [
        {
          "type": "output_text",
          "text": "string",
          "annotations": [
            null
          ],
          "logprobs": [
            null
          ]
        }
      ]
    }
  ],
  "output_text": "string",
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0,
    "total_tokens": 0,
    "cost": 0,
    "cost_currency": "USD",
    "cost_eur": 0,
    "is_byok": true,
    "cost_details": {
      "property1": 0,
      "property2": 0
    },
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "property1": null,
    "property2": null
  },
  "completed_at": 0,
  "error": {
    "code": "string",
    "message": "string"
  },
  "incomplete_details": {
    "reason": "max_output_tokens"
  },
  "billing": {
    "payer": "string"
  },
  "frequency_penalty": 0,
  "conversation": {
    "id": "string",
    "property1": null,
    "property2": null
  },
  "instructions": "string",
  "max_output_tokens": 0,
  "max_tool_calls": 0,
  "moderation": null,
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": "string",
  "prompt": {
    "property1": null,
    "property2": null
  },
  "prompt_cache_key": "string",
  "prompt_cache_retention": "string",
  "reasoning": {
    "effort": "none",
    "generate_summary": "auto",
    "summary": "auto",
    "property1": null,
    "property2": null
  },
  "safety_identifier": "string",
  "store": true,
  "temperature": 0,
  "text": {
    "format": {
      "type": "text",
      "description": "string",
      "name": "string",
      "schema": null,
      "strict": true
    },
    "verbosity": "string"
  },
  "tool_choice": "string",
  "tools": [
    null
  ],
  "top_logprobs": 0,
  "top_p": 0,
  "truncation": "auto",
  "user": "string",
  "metadata": {
    "property1": "string",
    "property2": "string"
  },
  "background": true,
  "service_tier": "string",
  "property1": null,
  "property2": null
}