Call it from your code
from openai import OpenAI
client = OpenAI(base_url="https://devsaio.lol/v1", api_key="dsk_...")
r = client.chat.completions.create(
model="claude-opus-5-5",
messages=[{"role": "user", "content": "Hello!"}],
)
print(r.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://devsaio.lol/v1", apiKey: process.env.DEVSAIO_API_KEY });
const r = await client.chat.completions.create({
model: "claude-opus-5-5",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(r.choices[0].message.content);curl https://devsaio.lol/v1/chat/completions \
-H "Authorization: Bearer $DEVSAIO_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"claude-opus-5-5","messages":[{"role":"user","content":"Hello!"}]}'export ANTHROPIC_BASE_URL="https://devsaio.lol" export ANTHROPIC_AUTH_TOKEN="dsk_..." export ANTHROPIC_MODEL="claude-opus-5-5" claude
Works with any OpenAI-compatible SDK or tool. Setup guides for Claude Code, Codex and Cursor
What it costs in practice
- A short chat message
- ≈ $0.01 (1K tokens in, 500 out)
- Summarise a long document
- ≈ $0.23 (50K in, 1K out)
- A coding-agent session
- ≈ $2.10 (400K in, 20K out)
Estimates from the list price above. You are charged the exact tokens each call reports. Failed calls are free.
More from Anthropic
All Anthropic models →
Input / 1M$10.50Output / 1M$52.50
Input / 1M$10.50Output / 1M$52.50
Input / 1M$1.05Output / 1M$5.25
Input / 1M$0.105Output / 1M$0.525
Input / 1M$5.25Output / 1M$26.25
Input / 1M$5.25Output / 1M$26.25
Compare with other labs
Full price list →
Input / 1M$5.25Output / 1M$31.50
Input / 1M$1.26Output / 1M$0.315
Input / 1M$0.294Output / 1M$0.441
Input / 1M$0.147Output / 1M$0.294
Input / 1M$0.462Output / 1M$1.386
Input / 1M$0.4568Output / 1M$0.9135