Studios

Messages

The Anthropic Messages format, for Claude Code and Anthropic SDKs.

Create a message

POST/api/v1/messagesPer token · credits only

The Anthropic Messages format on the same menu as Chat Completions. Claude Code and the Anthropic SDKs work once their base URL is https://mystudios.fun/api. Requests and responses pass through unchanged.

Request body

modelstringrequiredA model id from the menu. Dated ids like claude-sonnet-5-20250929resolve to the menu model. Haiku ids get the lowest-priced Claude. Smart Router isn't available here.
max_tokensintegerrequiredThe most tokens the reply can use, up to 32,768.
messagesobject[]requiredThe conversation, oldest first. Each message has a role and content.user · assistant
systemstring | object[]The system prompt.
streambooleanStream Anthropic's server-sent events.
toolsobject[]Tools the model can call, in Anthropic's format.

Other Anthropic parameters pass through to the model.

Example request

import Anthropic from "@anthropic-ai/sdk";​const client = new Anthropic({  apiKey: process.env.CLAWHUNTER_API_KEY,  baseURL: "https://mystudios.fun/api",});​const message = await client.messages.create({  model: "claude-sonnet-5-5",  max_tokens: 1024,  messages: [{ role: "user", content: "Why is the sky blue?" }],});

Response

An Anthropic message, exactly as the model returned it. The charge shows in your account's usage.

Response
{  "id": "msg_…",  "type": "message",  "role": "assistant",  "model": "claude-sonnet-5-5",  "content": [    { "type": "text", "text": "Sunlight scatters off molecules in the air…" }  ],  "stop_reason": "end_turn",  "usage": { "input_tokens": 14, "output_tokens": 180 }}

Billing and limits

  • Prepaid credits only. This endpoint doesn't take x402.
  • Send your key as x-api-key or as a Bearer token.
  • Billed per token at the same rates as Chat Completions, listed on Models.
  • The call reserves your input plus max_tokens, then settles for what you used. Your balance has to cover the reserve.
  • max_tokens is required and caps at 32,768.
  • Input caps at 800,000 characters across messages, system, and tools. A larger request returns 413.
  • Eligible models draw on your daily free allowance first.
  • Errors come back in Anthropic's error format.
  • A rejected or failed request is not charged.