Skip to main content
POST
/
v1
/
messages
Messages API
curl --request POST \
  --url https://api.unifically.com/v1/messages \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "max_tokens": 123,
  "messages": [
    {}
  ],
  "system": {},
  "stream": true,
  "temperature": 123,
  "top_p": 123,
  "stop_sequences": [
    {}
  ],
  "tools": [
    {}
  ],
  "tool_choice": {}
}
'
{
  "id": "msg_abc123",
  "type": "message",
  "role": "assistant",
  "model": "anthropic/claude-sonnet-4-6",
  "content": [
    {
      "type": "text",
      "text": "Quantum computing harnesses quantum mechanical phenomena..."
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 18,
    "output_tokens": 72
  }
}
The /v1/messages endpoint provides an Anthropic Messages API-compatible interface for text generation. Use the same request format as the Anthropic Messages API — swap the base URL to https://api.unifically.com and pass any supported model ID in the model field.
All LLM models support this endpoint, including Cursor, OpenAI, and Anthropic models.

​
Create Message

POST /v1/messages

​
Request

curl -X POST https://api.unifically.com/v1/messages \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "anthropic/claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Explain quantum computing in one paragraph."}
    ]
  }'

​
Request Parameters

​
model
string
required
Model identifier in provider/model-name format. See Available LLM Models.
​
max_tokens
integer
required
Maximum number of tokens to generate before stopping.
​
messages
array
required
Array of message objects with role (user or assistant) and content (string or content blocks array).
​
system
string | array
System prompt providing context and instructions to the model.
​
stream
boolean
If true, the response is streamed using server-sent events. Default: false.
​
temperature
number
Sampling temperature between 0 and 1.
​
top_p
number
Nucleus sampling parameter. Use either temperature or top_p, not both.
​
stop_sequences
array
Custom sequences that cause the model to stop generating.
​
tools
array
Definitions of tools the model may use. Each tool includes name, description, and input_schema.
​
tool_choice
object
Controls tool usage. Default: { "type": "auto" }.

​
System Prompt Example

curl -X POST https://api.unifically.com/v1/messages \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "openai/gpt-5.4",
    "max_tokens": 512,
    "system": "You are a helpful coding assistant. Be concise.",
    "messages": [
      {"role": "user", "content": "What is a closure in JavaScript?"}
    ]
  }'

​
Response

{
  "id": "msg_abc123",
  "type": "message",
  "role": "assistant",
  "model": "anthropic/claude-sonnet-4-6",
  "content": [
    {
      "type": "text",
      "text": "Quantum computing harnesses quantum mechanical phenomena..."
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 18,
    "output_tokens": 72
  }
}

​
Streaming Response

When stream: true, the API returns text/event-stream with Anthropic-compatible event types (message_start, content_block_delta, message_stop, etc.): 
curl -X POST https://api.unifically.com/v1/messages \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "cursor/composer-2.5-fast",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

​
Supported Models

ModelProvider
cursor/composer-2.5Cursor
cursor/composer-2.5-fastCursor
openai/gpt-5.4-miniOpenAI
openai/gpt-5.4-nanoOpenAI
openai/gpt-5.4OpenAI
openai/gpt-5.5OpenAI
anthropic/claude-sonnet-4-6Anthropic
anthropic/claude-opus-4-6Anthropic
anthropic/claude-opus-4-7Anthropic
anthropic/claude-opus-4-8Anthropic
See individual model pages under LLM Models for details.

​
SDK Compatibility

Point the Anthropic SDK at Unifically by changing the base URL: 
import anthropic

client = anthropic.Anthropic(
    api_key="YOUR_API_KEY",
    base_url="https://api.unifically.com"
)

message = client.messages.create(
    model="anthropic/claude-opus-4-7",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}]
)
print(message.content[0].text)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.UNIFICALLY_API_KEY,
  baseURL: "https://api.unifically.com",
});

const message = await client.messages.create({
  model: "anthropic/claude-sonnet-4-6",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello!" }],
});