Messages

Anthropic Messages API — required by Claude Code.

Create a message (Anthropic Messages API)

POST

https://api.hyphen-solution.com

/v1/messages

Anthropic-compatible Messages API. Required by Claude Code (ANTHROPIC_BASE_URL points here). The gateway accepts Anthropic-format requests and translates to the upstream provider.

Create a message (Anthropic Messages API) › Headers

anthropic-version

string

Accepted for compatibility with Anthropic-format clients. The gateway handles the upstream translation; the header does not change routing.

Create a message (Anthropic Messages API) › Request Body

MessagesRequest

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

max_tokens

integer · min: 1 · required

Maximum number of tokens to generate. Required by the Anthropic Messages format.

object[] · required

Alternating user / assistant turns, oldest first.

system

string

Optional system prompt — a top-level field here, not a message role.

temperature

number · min: 0 · max: 1

Sampling temperature, 0–1 in the Anthropic format. Lower is more deterministic.

stream

boolean

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

Default: false

stop_sequences

string[]

Custom sequences that stop generation.

Create a message (Anthropic Messages API) › Responses

An Anthropic-format message.

MessagesResponse

id

string

type

string

role

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.

object[]

Content blocks — for text generation, one text block.

stop_reason

string

end_turn, max_tokens, or stop_sequence.

stop_sequence

string | null

Which stop_sequences entry matched, if any.

object

POST/v1/messages

curl https://api.hyphen-solution.com/v1/messages \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <token>' \
  --data '{
  "model": "minimax-m3",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Explain what a gateway does, briefly."
    }
  ]
}'

Example Request Body

{
  "model": "minimax-m3",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Explain what a gateway does, briefly."
    }
  ]
}

json

application/json

Example Responses

{
  "id": "msg_9f8e7d6c5b4a",
  "type": "message",
  "role": "assistant",
  "model": "minimax-m3",
  "content": [
    {
      "type": "text",
      "text": "A gateway sits between your tools and many model providers, giving them one URL, one key, and one bill."
    }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 16,
    "output_tokens": 28
  }
}

json

application/json

Responses Models

Create a message (Anthropic Messages API)

POST

https://api.hyphen-solution.com

/v1/messages

Anthropic-compatible Messages API. Required by Claude Code (ANTHROPIC_BASE_URL points here). The gateway accepts Anthropic-format requests and translates to the upstream provider.

Create a message (Anthropic Messages API) › Headers

anthropic-version

string

Accepted for compatibility with Anthropic-format clients. The gateway handles the upstream translation; the header does not change routing.

Create a message (Anthropic Messages API) › Request Body

MessagesRequest

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

max_tokens

integer · min: 1 · required

Maximum number of tokens to generate. Required by the Anthropic Messages format.

object[] · required

Alternating user / assistant turns, oldest first.

system

string

Optional system prompt — a top-level field here, not a message role.

temperature

number · min: 0 · max: 1

Sampling temperature, 0–1 in the Anthropic format. Lower is more deterministic.

stream

boolean

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

Default: false

stop_sequences

string[]

Custom sequences that stop generation.

Create a message (Anthropic Messages API) › Responses

An Anthropic-format message.

MessagesResponse

id

string

type

string

role

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.

object[]

Content blocks — for text generation, one text block.

stop_reason

string

end_turn, max_tokens, or stop_sequence.

stop_sequence

string | null

Which stop_sequences entry matched, if any.

object