Gemini 3.8 Flash in GitHub Copilot
Google - Versatile
In GitHub Copilot, Gemini 3.8 Flash costs $0.75 per 1M input tokens and $3.75 per 1M output tokens, billed as AI credits at $0.01 each. A typical daily-coding request works out to about 1 credits (about $0.01) with auto model selection on. Rates verified against GitHub's rate sheet on 2026-08-17.
Token rates
- Input / 1M
- $0.75
- Cached input / 1M
- $0.08
- Output / 1M
- $3.75
- Cost per credit
- $0.01
Promotional rate, published as running through 2026-12-31. GitHub has not published the rate that follows it.
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 | 0.5 | 0.5 | $0.00 |
| Daily coding request | 1.0 | 1.1 | $0.01 |
| Agent session step | 3.1 | 3.5 | $0.03 |
At about 1.0 credits per daily-coding request, Gemini 3.8 Flash ranks #7 of 22 current models by cost, about 3.4x the cheapest (GPT-5.6 Luna).
Requests per plan allowance
Daily-coding requests the included monthly credits buy, before any overage.
| Plan | Credits / month | Requests |
|---|---|---|
| Copilot Pro | 1,500 | 1,576 |
| Copilot Pro+ | 7,000 | 7,354 |
| Copilot Max | 20,000 | 21,013 |
| Copilot Business | 1,900 | 1,996 |
| Copilot Enterprise | 3,900 | 4,097 |