Messages API

Send requests using the Anthropic Messages API format for Claude models

The Messages API (/v1/messages) provides direct compatibility with the Anthropic Messages API format. Use this endpoint when working with Anthropic Claude models and features like interleaved thinking, tool calling, and multi-turn conversations.

The Messages API (/v1/messages) is fully supported on the Enterprise plan using https://enterprise.blackbox.ai. On standard plans (https://api.blackbox.ai), this endpoint may not work as expected. For the best experience, use an Enterprise API key.

Basic Request

Python

import os
import requests

response = requests.post(
    'https://enterprise.blackbox.ai/v1/messages',
    headers={
        'Content-Type': 'application/json',
        'Authorization': f"Bearer {os.environ['BLACKBOX_API_KEY']}",
        'anthropic-version': '2023-06-01',
    },
    json={
        'model': 'blackboxai/anthropic/claude-sonnet-4.5',
        'max_tokens': 1024,
        'messages': [
            {'role': 'user', 'content': 'What is the capital of France?'}
        ],
    },
)

result = response.json()
print(result['content'][0]['text'])

const response = await fetch("https://enterprise.blackbox.ai/v1/messages", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
    "anthropic-version": "2023-06-01"
  },
  body: JSON.stringify({
    model: "blackboxai/anthropic/claude-sonnet-4.5",
    max_tokens: 1024,
    messages: [
      { role: "user", content: "What is the capital of France?" }
    ]
  })
});

const result = await response.json();
console.log(result.content[0].text);

curl https://enterprise.blackbox.ai/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "blackboxai/anthropic/claude-sonnet-4.5",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "What is the capital of France?"}
    ]
  }'

Response Format

{
  "id": "gen_01KJRNETDECKXVWK0YX46WSHDY",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "The capital of France is Paris."
    }
  ],
  "model": "blackboxai/anthropic/claude-sonnet-4.5",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 19,
    "output_tokens": 10,
    "total_tokens": 29,
    "cache_read_input_tokens": 0,
    "cache_creation_input_tokens": 0
  }
}

---

System Prompt

Use the system parameter to set the model’s behavior for the entire conversation.

Python

import os
import requests

response = requests.post(
    'https://enterprise.blackbox.ai/v1/messages',
    headers={
        'Content-Type': 'application/json',
        'Authorization': f"Bearer {os.environ['BLACKBOX_API_KEY']}",
        'anthropic-version': '2023-06-01',
    },
    json={
        'model': 'blackboxai/anthropic/claude-sonnet-4.5',
        'max_tokens': 256,
        'system': 'You are a helpful pirate. Always respond in pirate speak.',
        'messages': [
            {'role': 'user', 'content': 'What is 2 + 2?'}
        ],
    },
)

result = response.json()
print(result['content'][0]['text'])

const response = await fetch("https://enterprise.blackbox.ai/v1/messages", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
    "anthropic-version": "2023-06-01"
  },
  body: JSON.stringify({
    model: "blackboxai/anthropic/claude-sonnet-4.5",
    max_tokens: 256,
    system: "You are a helpful pirate. Always respond in pirate speak.",
    messages: [
      { role: "user", content: "What is 2 + 2?" }
    ]
  })
});

const result = await response.json();
console.log(result.content[0].text);

curl https://enterprise.blackbox.ai/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "blackboxai/anthropic/claude-sonnet-4.5",
    "max_tokens": 256,
    "system": "You are a helpful pirate. Always respond in pirate speak.",
    "messages": [
      {"role": "user", "content": "What is 2 + 2?"}
    ]
  }'

Response

{
  "id": "gen_01KJRNEX4M6JD4GDPF4K5MK2J0",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Arrr, that be an easy bit o' mathematics, matey! 2 + 2 equals 4, as sure as the seven seas be salty!"
    }
  ],
  "model": "blackboxai/anthropic/claude-sonnet-4.5",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 30,
    "output_tokens": 60
  }
}

---

Multi-Turn Conversations

Pass previous messages as an array of alternating user and assistant messages to maintain conversation context.

Python

import os
import requests

response = requests.post(
    'https://enterprise.blackbox.ai/v1/messages',
    headers={
        'Content-Type': 'application/json',
        'Authorization': f"Bearer {os.environ['BLACKBOX_API_KEY']}",
        'anthropic-version': '2023-06-01',
    },
    json={
        'model': 'blackboxai/anthropic/claude-sonnet-4.5',
        'max_tokens': 256,
        'messages': [
            {'role': 'user', 'content': 'My name is Alice.'},
            {'role': 'assistant', 'content': 'Nice to meet you, Alice! How can I help you today?'},
            {'role': 'user', 'content': "What's my name?"},
        ],
    },
)

result = response.json()
print(result['content'][0]['text'])

const response = await fetch("https://enterprise.blackbox.ai/v1/messages", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
    "anthropic-version": "2023-06-01"
  },
  body: JSON.stringify({
    model: "blackboxai/anthropic/claude-sonnet-4.5",
    max_tokens: 256,
    messages: [
      { role: "user", content: "My name is Alice." },
      { role: "assistant", content: "Nice to meet you, Alice! How can I help you today?" },
      { role: "user", content: "What's my name?" }
    ]
  })
});

const result = await response.json();
console.log(result.content[0].text);

curl https://enterprise.blackbox.ai/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "blackboxai/anthropic/claude-sonnet-4.5",
    "max_tokens": 256,
    "messages": [
      {"role": "user", "content": "My name is Alice."},
      {"role": "assistant", "content": "Nice to meet you, Alice! How can I help you today?"},
      {"role": "user", "content": "What is my name?"}
    ]
  }'

Response

{
  "id": "gen_01KJRNF1RP8DWKJ3M59JDAQRHX",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Your name is Alice, as you just told me."
    }
  ],
  "model": "blackboxai/anthropic/claude-sonnet-4.5",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 37,
    "output_tokens": 14
  }
}

---

Request Headers

Authorization · string · required

API Key in the format Bearer <api_key>. Get yours from here.

anthropic-version · string · required

Anthropic API version. Use 2023-06-01.

anthropic-beta · string

Optional beta features. For example, interleaved-thinking-2025-05-14 for legacy interleaved thinking support.

Request Parameters

model · string · required

The model ID. Supported models include:

• blackboxai/anthropic/claude-opus-4.8
• blackboxai/anthropic/claude-opus-4.7
• blackboxai/anthropic/claude-opus-4.6
• blackboxai/anthropic/claude-opus-4.5
• blackboxai/anthropic/claude-sonnet-4.6
• blackboxai/anthropic/claude-sonnet-4.5

max_tokens · integer · required

Maximum number of tokens to generate.

messages · array · required

Array of message objects with role (user or assistant) and content fields.

system · string

System prompt for the conversation.

tools · array

Array of tool definitions using the Anthropic input_schema format. See Tool Calling.

thinking · object

Configuration for extended / interleaved thinking. See Interleaved Thinking.

Response Fields

id · string

Unique message identifier.

type · string

Always "message".

role · string

Always "assistant".

content · array

Array of content blocks. Each block has a type field:

• text — Text response with a text field
• tool_use — Tool call with id, name, and input fields
• thinking — Thinking block with a thinking field (when thinking is enabled)

stop_reason · string

Why the model stopped generating:

• end_turn — Natural completion
• tool_use — Model wants to call a tool
• max_tokens — Hit the token limit

usage · object

Token usage with input_tokens and output_tokens.

Supported Models

Model	Model ID	Tool Calling	Interleaved Thinking
Claude Opus 4.6	blackboxai/anthropic/claude-opus-4.6	✓	✓
Claude Opus 4.5	blackboxai/anthropic/claude-opus-4.5	✓	✓
Claude Sonnet 4.6	blackboxai/anthropic/claude-sonnet-4.6	✓	✓
Claude Sonnet 4.5	blackboxai/anthropic/claude-sonnet-4.5	✓	✓

Tool Calling

Define tools and build multi-turn agentic loops

Interleaved Thinking

Enable reasoning between tool calls