POST
/
api
/
v1
/
messages
Messages
curl --request POST \
  --url https://www.llmadaptive.uk/api/v1/messages \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "<string>",
  "messages": [
    {}
  ],
  "max_tokens": 123,
  "role": "<string>",
  "content": {},
  "system": "<string>",
  "temperature": 123,
  "top_p": 123,
  "top_k": 123,
  "stop_sequences": [
    {}
  ],
  "model_router": {
    "cost_bias": 123,
    "models": [
      {}
    ]
  },
  "fallback": {
    "enabled": true,
    "mode": "<string>"
  }
}'
{
  "id": "<string>",
  "type": "<string>",
  "role": "<string>",
  "content": [
    {}
  ],
  "model": "<string>",
  "stop_reason": "<string>",
  "usage": {
    "input_tokens": 123,
    "output_tokens": 123
  },
  "provider": "<string>",
  "cache_tier": "<string>"
}

​
Overview

The Messages endpoint provides an Anthropic Claude-compatible API with intelligent routing across multiple providers. Use this endpoint when you prefer Anthropic’s message format or are migrating from Claude.

​
Endpoint

POST https://www.llmadaptive.uk/api/v1/messages

​
Authentication

curl https://www.llmadaptive.uk/api/v1/messages \
  -H "Authorization: Bearer your-adaptive-key" \
  -H "Content-Type: application/json"

​
Basic Request

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

const anthropic = new Anthropic({
  apiKey: 'your-adaptive-key',
  baseURL: 'https://www.llmadaptive.uk/api/v1'
});

const message = await anthropic.messages.create({
  model: '', // Empty for intelligent routing
  max_tokens: 1000,
  messages: [
    { role: 'user', content: 'Hello! How are you?' }
  ]
});

console.log(message.content[0].text);

​
Request Parameters

​
Required Parameters

​
model
string
required
Model identifier. Use "" (empty string) for intelligent routing.
​
messages
array
required
Array of message objects representing the conversation history.
​
max_tokens
integer
required
Maximum number of tokens to generate in the response.

​
Message Object

​
role
string
required
The role of the message sender. Must be either "user" or "assistant".
​
content
string or array
required
The content of the message. Can be a string or array of content blocks for multimodal inputs.

​
Optional Parameters

​
system
string
System prompt to guide the model’s behavior.
​
temperature
number
Sampling temperature between 0 and 1. Higher values make output more random.
​
top_p
number
Nucleus sampling parameter. Controls diversity of generated text.
​
top_k
integer
Top-k sampling parameter. Limits vocabulary to top k tokens.
​
stop_sequences
array
Array of strings where the model should stop generating.

​
Intelligent Routing Parameters

These additional parameters control Adaptive’s intelligent routing:
​
model_router
object
Configuration for intelligent model selection.
​
fallback
object
Fallback configuration for provider failures.

​
Example with Intelligent Routing

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

const anthropic = new Anthropic({
  apiKey: 'your-adaptive-key',
  baseURL: 'https://www.llmadaptive.uk/api/v1'
});

const message = await anthropic.messages.create({
  model: '',
  max_tokens: 1000,
  system: 'You are a helpful AI assistant focused on clear, concise answers.',
  messages: [
    { 
      role: 'user', 
      content: 'Explain machine learning in simple terms' 
    }
  ],
  temperature: 0.7,
  
  // Adaptive intelligent routing
  model_router: {
    cost_bias: 0.3, // Favor cost savings
    models: [
      { provider: 'anthropic' },
      { provider: 'openai' },
      { provider: 'deepseek' }
    ]
  },
  
  // Fallback configuration
  fallback: {
    enabled: true,
    mode: 'race'
  }
});

console.log(message.content[0].text);

​
Response Format

{
  "id": "msg_abc123",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Machine learning is a method of teaching computers to learn patterns from data..."
    }
  ],
  "model": "claude-3-haiku",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 25,
    "output_tokens": 150
  },
  "provider": "anthropic",      // Which provider was used
  "cache_tier": "none"          // Cache performance info
}

​
Response Fields

​
id
string
Unique identifier for the message.
​
type
string
Always “message” for this endpoint.
​
role
string
Always “assistant” for responses.
​
content
array
Array of content blocks containing the generated response.
​
model
string
The specific model that generated the response.
​
stop_reason
string
Reason the model stopped generating: “end_turn”, “max_tokens”, or “stop_sequence”.
​
usage
object
Token usage information.
​
provider
string
Adaptive Extension: Which AI provider was selected for this request.
​
cache_tier
string
Adaptive Extension: Cache performance information.

​
Streaming

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

const anthropic = new Anthropic({
  apiKey: 'your-adaptive-key',
  baseURL: 'https://www.llmadaptive.uk/api/v1'
});

const stream = await anthropic.messages.create({
  model: '',
  max_tokens: 1000,
  messages: [
    { role: 'user', content: 'Tell me a story about AI' }
  ],
  stream: true
});

for await (const messageStreamEvent of stream) {
  if (messageStreamEvent.type === 'content_block_delta') {
    process.stdout.write(messageStreamEvent.delta.text);
  }
}

​
Migration from Claude

Simply change the base URL - everything else works the same: 
import anthropic

client = anthropic.Anthropic(api_key="sk-ant-your-key")

message = client.messages.create(
    model="claude-3-sonnet-20240229",
    max_tokens=1000,
    messages=[{"role": "user", "content": "Hello"}]
)

​
Error Handling

The endpoint returns standard Anthropic-compatible error responses: 
{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "max_tokens is required"
  }
}

​
Next Steps

Chat Completions

Use OpenAI-compatible format for chat completions

Intelligent Routing

Learn more about model selection and optimization