Chat

OpenAI Chat Completions — the default surface.

Create a chat completion

POST

https://api.hyphen-solution.com

/v1/chat/completions

OpenAI-compatible Chat Completions endpoint. This is the default surface used by the OpenAI SDK, Cursor, Cline, Aider, Continue, Hermes and most OpenAI-compatible clients.

Create a chat completion › Request Body

ChatCompletionRequest

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

ChatMessage[] · required

temperature

number · min: 0 · max: 2

Default: 1

max_tokens

integer · min: 1

stream

boolean

Set true for a Server-Sent Events stream of deltas.

Default: false

Create a chat completion › Responses

A chat completion.

ChatCompletionResponse

id

string

object

string

created

integer

model

string

object[]

Usage

POST/v1/chat/completions

curl https://api.hyphen-solution.com/v1/chat/completions \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <token>' \
  --data '{
  "model": "m3",
  "messages": [
    {
      "role": "user",
      "content": "Say hello in one sentence."
    }
  ]
}'

Example Request Body

{
  "model": "m3",
  "messages": [
    {
      "role": "user",
      "content": "Say hello in one sentence."
    }
  ]
}

json

application/json

Example Responses

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1730000000,
  "model": "m3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "user",
        "content": "Hello!"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 24,
    "total_tokens": 36
  }
}

json

application/json

Responses

Create a chat completion

POST

https://api.hyphen-solution.com

/v1/chat/completions

OpenAI-compatible Chat Completions endpoint. This is the default surface used by the OpenAI SDK, Cursor, Cline, Aider, Continue, Hermes and most OpenAI-compatible clients.

Create a chat completion › Request Body

ChatCompletionRequest

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

ChatMessage[] · required

temperature

number · min: 0 · max: 2

Default: 1

max_tokens

integer · min: 1

stream

boolean

Set true for a Server-Sent Events stream of deltas.

Default: false

Create a chat completion › Responses

A chat completion.

ChatCompletionResponse

id

string

object

string

created

integer

model

string

object[]

Usage