Responses

OpenAI Responses API — required by Codex CLI.

Create a model response (Responses API)

POST

https://api.hyphen-solution.com

/v1/responses

OpenAI Responses API. Required by Codex CLI (wire_api = "responses"). Most upstream providers only speak Chat Completions — the Hyphen gateway (LiteLLM) performs the Responses ⇄ Chat Completions translation so Codex can reach every model in the catalog.

Because this surface is bridged to Chat Completions upstream, the core Responses parameters below are supported; upstream-specific Responses features (built-in tools, previous_response_id state) are not. Unsupported parameters are dropped rather than rejected.

Create a model response (Responses API) › Request Body

ResponsesRequest

model

Model · enum · required

A model ID from the current catalog — real provider model names, all MiniMax. The core tiers are minimax-m3 (flagship), minimax-m2.7 (balanced daily driver) and minimax-m2.5 (fast); the -highspeed variants are latency-tuned versions of their standard siblings at roughly 2x the price; minimax-m2.1 and minimax-m2 are older M-series generations; minimax-m2-her is role-play/dialogue chat tuning; minimax-text-01 is the long-context text model. There are no invented aliases; any other ID returns an error. The catalog can change with notice.

Enum values:

minimax-m3

minimax-m2.7

minimax-m2.7-highspeed

minimax-m2.5

minimax-m2.5-highspeed

minimax-m2.1

minimax-m2.1-highspeed

minimax-m2

required

The input — a plain string, or a list of typed input items (e.g. {"role": "user", "content": "..."}).

instructions

string

System-style instructions for the model.

max_output_tokens

integer · min: 1

Maximum number of tokens to generate in the response.

stream

boolean

Set true for a Server-Sent Events stream of response events.

Default: false

Create a model response (Responses API) › Responses

A model response.

ResponsesResponse

id

string

object

string

model

string

The model that actually served the request. During a provider incident this may be a smaller model of the same family as the one you requested.

status

string

completed, incomplete, or failed.

object[]

Output items — for text generation, one assistant message.

ResponsesUsage

Token usage in Responses-API shape.

POST/v1/responses

curl https://api.hyphen-solution.com/v1/responses \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <token>' \
  --data '{
  "model": "minimax-m3",
  "input": "Write a haiku about gateways."
}'

Example Request Body

{
  "model": "minimax-m3",
  "input": "Write a haiku about gateways."
}

json

application/json

Example Responses

{
  "id": "resp_9f8e7d6c5b4a",
  "object": "response",
  "model": "minimax-m3",
  "status": "completed",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Requests converge —\none door to every model,\nkeys turn quietly."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 14,
    "output_tokens": 21,
    "total_tokens": 35
  }
}

json

application/json

Chat Messages

Create a model response (Responses API)

POST

https://api.hyphen-solution.com

/v1/responses

Create a model response (Responses API) › Request Body

ResponsesRequest

model

Model · enum · required

Enum values:

minimax-m3

minimax-m2.7

minimax-m2.7-highspeed

minimax-m2.5

minimax-m2.5-highspeed

minimax-m2.1

minimax-m2.1-highspeed

minimax-m2

required

The input — a plain string, or a list of typed input items (e.g. {"role": "user", "content": "..."}).

instructions

string

System-style instructions for the model.

max_output_tokens

integer · min: 1

Maximum number of tokens to generate in the response.

stream

boolean

Set true for a Server-Sent Events stream of response events.

Default: false

Create a model response (Responses API) › Responses

A model response.

ResponsesResponse

id

string

object

string

model

string

The model that actually served the request. During a provider incident this may be a smaller model of the same family as the one you requested.

status

string

completed, incomplete, or failed.

object[]

Output items — for text generation, one assistant message.

ResponsesUsage

Token usage in Responses-API shape.