Anthropic Messages API — POST /v1/messages

The messages endpoint implements the Anthropic Messages API format, letting you use the official Anthropic SDK with Darkbloom by pointing it at https://api.darkbloom.dev. The request and response shapes follow the Anthropic API specification; the coordinator routes the request through the same provider dispatch and attestation pipeline as all other inference endpoints.

Authentication

All inference endpoints require a Bearer token:

Authorization: Bearer eigeninference-...

When using the Anthropic SDK, pass your Darkbloom API key as the api_key argument alongside the custom base_url.

Request

string

required

The model ID to use. See Models for the list of available IDs.

object[]

required

The conversation as an array of message objects. Each object must have:

role — "user" or "assistant"
content — the message text (string)

integer

required

Maximum number of tokens to generate. Required in Anthropic format.

string

An optional system prompt that sets context or persona for the assistant.

Response

The response follows the Anthropic response shape with a content array.

string

Unique identifier for the request.

string

Always "message".

string

Always "assistant".

object[]

Array of content blocks. Text responses contain a single block with type: "text".

Show content block fields

string

Content block type. "text" for standard responses.

string

The generated text (present when type is "text").

string

Why generation stopped. "end_turn" for natural completion; "max_tokens" if the token limit was reached.

object

Show usage fields

integer

Tokens consumed by the input.

integer

Tokens generated in the response.

Examples

import anthropic

client = anthropic.Anthropic(
    base_url="https://api.darkbloom.dev",
    api_key="eigeninference-...",
)

message = client.messages.create(
    model="qwen3.5-27b-claude-opus-8bit",
    max_tokens=512,
    system="You are a helpful assistant.",
    messages=[
        {"role": "user", "content": "What is the difference between a process and a thread?"}
    ],
)

print(message.content[0].text)

curl https://api.darkbloom.dev/v1/messages \
  -H "Authorization: Bearer eigeninference-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.5-27b-claude-opus-8bit",
    "max_tokens": 512,
    "system": "You are a helpful assistant.",
    "messages": [
      {"role": "user", "content": "What is the difference between a process and a thread?"}
    ]
  }'

Example response

{
  "id": "msg_01XFDUDYJgAACTvhG8fDDBEc",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "A process is an independent program with its own memory space..."
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 22,
    "output_tokens": 94
  }
}

Inference

Account

Network

Anthropic Messages API — POST /v1/messages

Authentication

Request

Response

Examples

Example response

​Authentication

​Request

​Response

​Examples

​Example response

Authentication

Request

Response

Examples

Example response