Anthropic compatibility

Set the Anthropic client’s base URL to https://api.saygm.com. The SDK adds /v1/messages and sends the GM key through the native x-api-key header.

Python

import os
from anthropic import Anthropic

client = Anthropic(
    base_url="https://api.saygm.com",
    api_key=os.environ["GM_API_KEY"],
)

message = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Say gm."}],
)
print(message.content[0].text)

Node.js

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

const client = new Anthropic({
  baseURL: "https://api.saygm.com",
  apiKey: process.env.GM_API_KEY,
});

const message = await client.messages.create({
  model: "claude-opus-4-8",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Say gm." }],
});
console.log(message.content[0].text);

Discover compatible models with:

curl -fsSL "https://api.saygm.com/v1/models?api_shape=messages"

Usage and cost

Every successful response carries settled cost inside usage, alongside the normal token counts:

{
  "usage": {
    "input_tokens": 12,
    "output_tokens": 9,
    "cost": 0.000140000,
    "cost_nano_usd": 140000
  }
}

cost is USD, rendered as a JSON number with exactly nine fractional digits — the amount actually settled against the account’s prepaid balance, not an estimate from /v1/models rates. cost_nano_usd is the same amount as an integer in nano-USD (1 nUSD = 10⁻⁹ USD), matching GET /v1/credits. Error responses carry neither field. See per-request cost for how to use the figure.