Anthropic's own API uses a format called the Messages API (POST /v1/messages). It's slightly different from OpenAI's: the system prompt is a top-level field, max_tokens is required, and the answer comes back as a list of content blocks. DEVSAIO accepts this format natively, so Anthropic tools work unchanged.
The base URL
For Anthropic-style clients, use the site root (the SDK adds /v1/messages itself):
https://devsaio.lolPython
pip install anthropicimport anthropic
client = anthropic.Anthropic(base_url="https://devsaio.lol", api_key="YOUR_KEY")
msg = client.messages.create(
model="claude-sonnet-4-6",
max_tokens=1024,
system="You are a concise assistant.",
messages=[{"role": "user", "content": "What is a race condition?"}],
)
print(msg.content[0].text)TypeScript
npm install @anthropic-ai/sdkimport Anthropic from "@anthropic-ai/sdk";
const client = new Anthropic({ baseURL: "https://devsaio.lol", apiKey: process.env.DEVSAIO_API_KEY });
const msg = await client.messages.create({
model: "claude-sonnet-4-6",
max_tokens: 1024,
messages: [{ role: "user", content: "Write a regex for UK postcodes." }],
});
console.log(msg.content[0].type === "text" ? msg.content[0].text : msg.content);curl
curl https://devsaio.lol/v1/messages \
-H "x-api-key: $DEVSAIO_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{"model": "claude-sonnet-4-6", "max_tokens": 512, "messages": [{"role": "user", "content": "Hi!"}]}'Which format should I use?
- Use Messages when a tool or SDK is built for Claude, or when you rely on Claude-specific response details.
- Use Chat Completions when you want one code path for every lab.
Both are billed the same way from your one balance. Next: set up Claude Code with a custom base URL.
Claude, GPT, Gemini, DeepSeek, image and video models through one OpenAI- and Anthropic-compatible endpoint. Prepaid, pay only for what you use.