Gemini 3.1 Pro in GitHub Copilot
Google - Powerful- preview
In GitHub Copilot, Gemini 3.1 Pro costs $2 per 1M input tokens and $12 per 1M output tokens, billed as AI credits at $0.01 each. A typical daily-coding request works out to about 2.8 credits (about $0.03) with auto model selection on. Rates verified against GitHub's rate sheet on 2026-07-14.
Token rates
- Input / 1M
- $2.00
- Cached input / 1M
- $0.20
- Output / 1M
- $12.00
- Cost per credit
- $0.01
Requests above 200,000 input tokens bill at the long-context tier ($4.00 in / $18.00 out per 1M).
Credits per request
Defined workload baskets, not measured tasks, with auto model selection on.
| Workload | Credits (auto on) | Credits (auto off) | Cost |
|---|---|---|---|
| Short chat turn | 1.4 | 1.6 | $0.01 |
| Daily coding request | 2.8 | 3.1 | $0.03 |
| Agent session step | 9.5 | 10.5 | $0.09 |
At about 2.8 credits per daily-coding request, Gemini 3.1 Pro ranks #13 of 22 current models by cost, about 9.8x the cheapest (GPT-5.4 nano).
Requests per plan allowance
Daily-coding requests the included monthly credits buy, before any overage.
| Plan | Credits / month | Requests |
|---|---|---|
| Copilot Pro | 1,500 | 534 |
| Copilot Pro+ | 7,000 | 2,492 |
| Copilot Max | 20,000 | 7,122 |
| Copilot Business | 1,900 | 676 |
| Copilot Enterprise | 3,900 | 1,388 |
Copilot rate vs direct API
GitHub Copilot bills Gemini 3.1 Pro at $2.00 in / $12.00 out per 1M. That input rate is the same as the direct Google gemini-3.1-pro-preview API price of $2.00 in / $12.00 out (validated 2026-06-15).