Anthropic-compatible API

What you need

1. An API key with the completions scope. See API keys and scopes.

2. The base URL https://idapt.app/api/anthropic/v1.

3. An active subscription, or your own provider key (BYOK). The free daily pool does not apply on this gateway.

Quick start

export ANTHROPIC_BASE_URL=https://idapt.app/api/anthropic/v1
export ANTHROPIC_API_KEY=uk_your_key_here

import anthropic

client = anthropic.Anthropic(
    base_url="https://idapt.app/api/anthropic/v1",
    api_key="uk_your_key_here",
)

message = client.messages.create(
    model="anthropic/claude-sonnet-4.6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
)

print(message.content[0].text)

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

const client = new Anthropic({
  baseURL: "https://idapt.app/api/anthropic/v1",
  apiKey: "uk_your_key_here",
});

const message = await client.messages.create({
  model: "openai/gpt-5.4-pro",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello!" }],
});

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

curl https://idapt.app/api/anthropic/v1/messages \
  -H "x-api-key: uk_your_key_here" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.5-flash",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Supported endpoints

• POST /messages, Create a message (streaming and non-streaming)

• GET /models, List available models (with pagination)

• GET /models/{id}, Get a single model's details

Streaming

Set stream: true to receive Server-Sent Events in the Anthropic streaming format. Events include message_start, content_block_start, content_block_delta, content_block_stop, message_delta, and message_stop.

Token usage is reported in message_start(input tokens) and message_delta(output tokens).

Models

Use the full model ID including the provider prefix, for example anthropic/claude-sonnet-4.6, openai/gpt-5.4-pro, or google/gemini-2.5-flash.

Call GET /models to see all available models, or browse the full catalog on the Models page.

Tool use

Tool definitions use the Anthropic format with input_schema. Tool results are sent as tool_result content blocks in user messages.

Usage and billing

Completions on this gateway need an active subscription or your own provider key, the same options as the OpenAI-compatible gateway. Calls without one return a 403 with code free_tier_requires_subscription. Language models bill at the prices shown in the app, and bring-your-own-key calls bill to your provider account.

Watch your spend on the usage page (/app/usage). See Plans, allowances, and credits for how the meters fit together.

Error handling

Errors follow the Anthropic format. Common status codes:

• 400, Bad request (missing model, invalid params, missing max_tokens)

• 401, Invalid or missing API key

• 403, Key lacks required permissions

• 429, Rate limit exceeded