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 works against any model alias.

Create a model response (Responses API) › Request Body

ResponsesRequest

model

ModelAlias · enum · required

A Hyphen model. Use a real model ID (m2.5, m2.7, m3, text) or one of the stable aliases that map onto them (hyphen-fast = m2.5, hyphen-sonnet = m2.7, hyphen-opus = m3).

Enum values:

m2.5

m2.7

text

hyphen-fast

hyphen-sonnet

hyphen-opus

required

A string, or a list of typed input items.

instructions

string

System-style instructions for the model.

max_output_tokens

integer · min: 1

stream

boolean

Default: false

Create a model response (Responses API) › Responses

A model response.

ResponsesResponse

id

string

object

string

model

string

object[]

Usage

POST/v1/responses

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

Example Request Body

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

json

application/json

Example Responses

{
  "id": "resp_abc123",
  "object": "response",
  "model": "m3",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "text"
        }
      ]
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 24,
    "total_tokens": 36
  }
}

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

ModelAlias · enum · required

A Hyphen model. Use a real model ID (m2.5, m2.7, m3, text) or one of the stable aliases that map onto them (hyphen-fast = m2.5, hyphen-sonnet = m2.7, hyphen-opus = m3).

Enum values:

m2.5

m2.7

text

hyphen-fast

hyphen-sonnet

hyphen-opus

required

A string, or a list of typed input items.

instructions

string

System-style instructions for the model.

max_output_tokens

integer · min: 1

stream

boolean

Default: false

Create a model response (Responses API) › Responses

A model response.

ResponsesResponse

id

string

object

string

model

string

object[]

Usage