OpenAI compatibility

Set the OpenAI client’s base URL to https://api.saygm.com/v1 and replace the OpenAI key with a GM key.

Python

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.saygm.com/v1",
    api_key=os.environ["GM_API_KEY"],
)

response = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{"role": "user", "content": "Say gm."}],
)
print(response.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.saygm.com/v1",
  apiKey: process.env.GM_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gpt-5.5",
  messages: [{ role: "user", content: "Say gm." }],
});
console.log(response.choices[0].message.content);

Responses API

Use the same client and base URL:

response = client.responses.create(
    model="gpt-5.5",
    input="Say gm.",
)
print(response.output_text)

Use /v1/models?api_shape=responses to discover models compatible with the Responses API.

Usage and cost

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

{
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 9,
    "total_tokens": 21,
    "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. Both fields appear on Chat Completions and Responses in the same place. Error responses carry neither. See per-request cost for how to use the figure.