> GitHub Models
GitHub Models was GitHub's hosted model playground, model catalog, inference API and bring-your-own-key service, and GitHub previously presented it as separate from GitHub Copilot. GitHub's official documentation now states that as of July 30, 2026, GitHub Models has been fully retired: the playground, model catalog, inference API and BYOK are no longer available to any customer. The same page directs users needing model access to Azure AI Foundry and users wanting AI workflows on GitHub to GitHub Copilot.
// pros
- GitHub's retirement notice is explicit and dated: playground, model catalog, inference API and BYOK are all listed as no longer available as of July 30, 2026.
- GitHub documents a replacement path rather than leaving users stranded, naming Azure AI Foundry for a broad model catalog and GitHub Copilot for AI-powered workflows on GitHub.
- The docs separate GitHub Models from GitHub Copilot explicitly, so Copilot plan and billing questions are unaffected by the retirement.
- Because the service is fully retired and had no separate paid tier, there is no current billing, quota expiry or data-retention exposure tied to it.
// cons
- The service cannot be used for new work: all four surfaces are retired with no free or paid access remaining.
- No migration credit or replacement free allowance is documented, so moving to the suggested alternatives means a new Azure AI Foundry account or a Copilot plan.
- Any third-party page still describing GitHub Models free model access or rate limits is out of date and should not be used for evaluation.
Do not start new projects on GitHub Models. Use Azure AI Foundry if you need a hosted multi-model catalog, or GitHub Copilot if the goal is AI assistance inside GitHub and your editor, and treat any surviving listing of GitHub Models free access as stale.
written by Mike Fleming, Uprouter editorial · verified against official sources September 16, 2026
No free tier
This provider does not offer a free tier as of our last verification (Sep 16, 2026). The cheapest way to try it is pay-as-you-go. If the provider adds a free tier, submit a correction and we’ll re-verify.
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Free tier (source-reported) | free | — | — | — | Free with a GitHub account, no credit card; free tier is ~50 calls/day (each higher-tier model has its own quota), with 429s on heavy use; stricter than Gemini Flash, positioned for learning and prototyping. |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Llama family | — | — | — |
| GPT-4o | — | — | 128k |
| GPT-4o-mini | — | — | 128k |
$ Does GitHub Models have a free tier?
No. GitHub Models does not offer a meaningful free tier — entry requires payment (pay-as-you-go or a plan). We mark this explicitly rather than showing a misleading zero.
$ How much does GitHub Models cost per 1M tokens?
GitHub Models does not publish simple per-1M-token pricing (it may bill per request, per output, or via a subscription plan). Check their official pricing page for exact figures.
$ Is GitHub Models safe to use?
Uprouter rates GitHub Models as low risk. High risk because the product no longer exists: GitHub's own docs state full retirement on July 30, 2026, covering the playground, catalog, inference API and BYOK. There are no plans, quotas, free tiers or rate limits left to evaluate, and any code written against its inference API would already be broken. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.
Raw community sentiment, shown unblended. Votes never feed into objective data fields like price, risk, or status — and never into sort order.
No published reviews yet — be the first.
// more_informationprice history · live status · risk & confidence · code snippets
price_history
No recorded changes yet.
live_status
full history →best-effort probes · not a guarantee · last 15h ago
| Checked | Status | Latency |
|---|---|---|
| 15h ago | up | 41ms |
| 1d ago | up | 44ms |
| 3d ago | up | 41ms |
| 4d ago | up | 39ms |
| 6d ago | up | 40ms |
| 7d ago | up | 21ms |
| 9d ago | up | 40ms |
| 10d ago | up | 43ms |
| 12d ago | up | 18ms |
| 13d ago | up | 17ms |
| 14d ago | up | 58ms |
| 15d ago | up | 19ms |
| 15d ago | up | 20ms |
| 16d ago | up | 19ms |
| 17d ago | up | 24ms |
| 18d ago | up | 44ms |
| 18d ago | up | 20ms |
| 19d ago | up | 22ms |
| 20d ago | up | 20ms |
| 21d ago | up | 19ms |
| 21d ago | up | 41ms |
| 22d ago | up | 50ms |
| 23d ago | up | 21ms |
| 24d ago | up | 48ms |
| 25d ago | up | 54ms |
| 26d ago | up | 41ms |
| 26d ago | up | 48ms |
| 27d ago | up | 54ms |
| 28d ago | up | 22ms |
| 29d ago | up | 20ms |
Uprouter runs its own probes; best-effort, not a guarantee. Probe results depend on our network location and cadence — for production, always use the provider’s own status page.
risk_&_confidence
High risk because the product no longer exists: GitHub's own docs state full retirement on July 30, 2026, covering the playground, catalog, inference API and BYOK. There are no plans, quotas, free tiers or rate limits left to evaluate, and any code written against its inference API would already be broken.
Confidence reflects how much verifiable evidence (official docs, probe history, community reports) backs this entry. Risk is our editorial assessment of operator reliability and terms — not financial advice.
code_snippets
# GitHub Models's own API — get a key from their dashboard
curl https://YOUR-PROVIDER-ENDPOINT/chat/completions \
-H "Authorization: Bearer THEIR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "llama-family",
"messages": [{ "role": "user", "content": "Hello" }]
}'Direct to the provider — Uprouter receives nothing; verify their current pricing before purchasing.
Ranked by neutral similarity signals only — live status, free-tier shape and free-credit proximity. Commercial relationships never influence this list.