Responses Protocol

Migration Notice: The Chat Completions API (/v1/chat/completions) has been removed. OpenModel supports the Responses protocol at POST /v1/responses; it does not provide a generic endpoint that accepts arbitrary OpenAI API formats. Migrate clients to the Responses request format rather than only changing the URL.

The Responses protocol exposes the OpenAI Responses API format at POST /v1/responses. It serves two providers: OpenAI and DashScope (Alibaba Cloud Qwen models).

Because both providers share the same endpoint and request shape, you use the OpenAI SDK for both — switching providers means changing only the model parameter. See the OpenAI SDK guide for installation and full examples.

Endpoint

POST https://api.openmodel.ai/v1/responses

The same base URL also serves the authenticated GET /v1/models model-list endpoint used by the OpenAI SDK (see Models).

Authentication

Pass your OpenModel API key as a bearer token:

Authorization: Bearer om-your-api-key

Switching providers

To target a different provider, change only the model parameter:

# OpenAI
client.responses.create(model="gpt-5.4", input="...")
# DashScope (Qwen)
client.responses.create(model="qwen3-max", input="...")

DashScope also supports the Messages protocol — use whichever matches your existing code.

Provider differences & playground

Select a provider below to see its example models, error-response format, and an interactive playground pre-filled with that provider's model.

Example models: gpt-4ogpt-4.1-mini
Error response format: Standard OpenAI format — errors carry error.code + error.type. This is the baseline all Responses providers are compared against.
Official documentation: OpenAI Responses API

These are example models; the available list may change. View all available models in the Console

Authorization

BearerAuth

AuthorizationBearer <token>

Include your API key: Authorization: Bearer om-your-api-key

In: header

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

model*string

The model ID to use for generating the response (e.g. gpt-5.5, gpt-5.4, gpt-5.4-mini).

input*|array<>

The input content for the response. Can be a simple text string for quick prompts, or an array of input items for multi-turn conversations and complex inputs including images.

instructions?string

System-level instructions that guide the model's behavior. Inserted at the beginning of the conversation as a developer message.

stream?boolean

If true, the response is returned as a stream of server-sent events (SSE).

Defaultfalse

temperature?number

Sampling temperature between 0 and 2. Lower values make output more focused and deterministic, while higher values make output more random and creative.

Range0 <= value <= 2

max_output_tokens?integer

The maximum number of tokens the model can generate in the response.

top_p?number

Nucleus sampling parameter. The model considers tokens with top_p cumulative probability mass.

Range0 <= value <= 1

tools?array<>

An array of tool definitions that the model may invoke.

tool_choice?|

Controls which tool (if any) the model calls.

text?object

Configuration for text response formatting. Use this to enforce structured output with a JSON schema.

store?boolean

Whether to store the response for later retrieval.

Defaulttrue

Response Body

`application/json`

curl -X POST "https://example.com/v1/responses" \  -H "Content-Type: application/json" \  -d '{    "model": "gpt-5.5",    "input": "Explain how API gateways work in 3 sentences."  }'

{
  "id": "resp_67ccf18ef5fc8190b16dbee19bc54e5f",
  "object": "response",
  "created_at": 1741484430,
  "model": "gpt-5.5",
  "output": [
    {
      "type": "message",
      "id": "msg_67ccf18ef5fc8190b16dbee19bc54e60",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "An API gateway acts as a single entry point for client requests, routing them to the appropriate backend services."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 18,
    "output_tokens": 52,
    "total_tokens": 70
  }
}

{
  "error": {
    "message": "string",
    "type": "string",
    "code": "string"
  }
}

{
  "error": {
    "message": "string",
    "type": "string",
    "code": "string"
  }
}

{
  "error": {
    "message": "string",
    "type": "string",
    "code": "string"
  }
}

Example models: qwen3.7-maxqwen3.6-plusqwen3.6-max-previewqwen3.6-flashqwen3-max
Error response format: The Messages endpoint returns DashScope's native error format — a root-level code/type with no error wrapper. The Responses endpoint uses the standard error.code + error.type shape.
Official documentation: DashScope Anthropic API

These are example models; the available list may change. View all available models in the Console

Authorization

BearerAuth

AuthorizationBearer <token>

Include your API key: Authorization: Bearer om-your-api-key

In: header

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

model*string

The DashScope model ID to use (e.g. qwen3-max).

input*|array<>

The input content for the response. Can be a simple text string for quick prompts, or an array of input items for multi-turn conversations and complex inputs including images.

instructions?string

System-level instructions that guide the model's behavior. Inserted at the beginning of the conversation as a developer message.

stream?boolean

If true, the response is returned as a stream of server-sent events (SSE).

Defaultfalse

temperature?number

Sampling temperature between 0 and 2. Lower values make output more focused and deterministic, while higher values make output more random and creative.

Range0 <= value <= 2

max_output_tokens?integer

The maximum number of tokens the model can generate in the response.

top_p?number

Nucleus sampling parameter. The model considers tokens with top_p cumulative probability mass.

Range0 <= value <= 1

tools?array<>

An array of tool definitions that the model may invoke.

tool_choice?|

Controls which tool (if any) the model calls.

store?boolean

Whether to store the response for later retrieval.

Defaulttrue

Response Body

`application/json`

curl -X POST "https://example.com/v1/responses" \  -H "Content-Type: application/json" \  -d '{    "model": "qwen3-max",    "input": "Explain how API gateways work in 3 sentences."  }'

{
  "id": "resp_67ccf18ef5fc8190b16dbee19bc54e5f",
  "object": "response",
  "created_at": 1741484430,
  "model": "qwen3-max",
  "output": [
    {
      "type": "message",
      "id": "msg_67ccf18ef5fc8190b16dbee19bc54e60",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "An API gateway acts as a single entry point for client requests, routing them to the appropriate backend services."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 18,
    "output_tokens": 52,
    "total_tokens": 70
  }
}

{
  "error": {
    "message": "string",
    "type": "string",
    "code": "string"
  }
}

{
  "error": {
    "message": "string",
    "type": "string",
    "code": "string"
  }
}

{
  "error": {
    "message": "string",
    "type": "string",
    "code": "string"
  }
}

Responses Protocol

200application/json

400application/json

401application/json

429application/json

200application/json

400application/json

401application/json

429application/json

On this page

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`