GitHub Models API key setup

Get your key

1. Open the GitHub Models API keys page: github.com/settings/tokens
2. Create an account and generate an API key.
3. Paste it into the Dracon BYOK provider keys, stored encrypted (AES-256-GCM), used browser-direct, works in every Dracon tool.

Get the key and test it

1. Open the GitHub Models API keys page: github.com/settings/tokens Create a key and copy the secret straight away.
2. Point your client at this provider's base URL: https://models.github.ai/inference It speaks the OpenAI-compatible shape, so an OpenAI SDK client works against it with no adapter: only the base URL and the key change.
3. Prove the endpoint answers before you trust it. Send one call with no Authorization header: a live endpoint answers 401 Unauthorized, because it is waiting for a bearer key. The wording of that error differs by provider (some say invalid_api_key, others incorrect_api_key or Token is invalid), so read the 401 as the signal, not the error text.
4. Paste the key into the Dracon BYOK provider keys ; stored encrypted, used browser-direct, no relay.
5. Compare other provider plans when this subscription does not match your usage or budget.

Test the key

Both examples read the key from the GITHUB_TOKEN environment variable, so the key stays out of the command line.

export GITHUB_TOKEN="<YOUR_API_KEY>"

curl https://models.github.ai/inference/chat/completions \
  -H "Authorization: Bearer $GITHUB_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-4o-mini","messages":[{"role":"user","content":"hi"}]}'

import os
from openai import OpenAI

# export GITHUB_TOKEN="<YOUR_API_KEY>" first
client = OpenAI(
    api_key=os.environ["GITHUB_TOKEN"],
    base_url="https://models.github.ai/inference",
)
resp = client.chat.completions.create(
    model="openai/gpt-4o-mini",
    messages=[{"role": "user", "content": "hi"}],
)
print(resp.choices[0].message.content)

Free tier

No recurring free tier advertised as of the last check (2026-10-27). Usage is billed per the provider's listed pricing. You pay them directly, no Dracon markup.

Rate limits: Service retired; see Azure AI Foundry for new projects.

Paid plans compared

Every tier GitHub Models publishes, with the price and the limit as the vendor states them, last checked 2026-10-27. Confirm with the provider before you buy. You pay them directly, no Dracon markup.

Official plan source: docs.github.com/en/github-models

Connection details

Base URL

https://models.github.ai/inference

API shape

OpenAI-compatible

Env var

GITHUB_TOKEN

Models

openai/gpt-4o-mini, openai/gpt-4o, meta/Llama-3.3-70B-Instruct

Model lineup

GPT-4o, GPT-4o mini, Claude 3.5 Sonnet, Llama 3.3, DeepSeek V3

Gotchas

Browser-direct chat is not available for this provider: GitHub retired GitHub Models inference on 2026-07-30. Use Azure AI Foundry or another provider.. Dracon provider keys still cover it for tools that run elsewhere (for example a LiteLLM chain from the Dracon Router builder).

Our verdicts on this kind of provider

Independent comparisons we keep current as pricing and free tiers shift. A guide is setup; a verdict is whether it's worth setting up.

• 22 of the 45 AI providers have a free tier. Only 7 are actually useful.
• Free AI rate limits, compared: which free tiers can do real work
• The AI price war: who cut what in July 2026