Gemini 3.5 Flash in GitHub Copilot

Google - Lightweight

In GitHub Copilot, Gemini 3.5 Flash costs $1.5 per 1M input tokens and $9 per 1M output tokens, billed as AI credits at $0.01 each. A typical daily-coding request works out to about 2.1 credits (about $0.02) with auto model selection on. Rates verified against GitHub's rate sheet on 2026-07-14.

Token rates

Input / 1M
$1.50
Cached input / 1M
$0.15
Output / 1M
$9.00
Cost per credit
$0.01

Credits per request

Defined workload baskets, not measured tasks, with auto model selection on.

WorkloadCredits (auto on)Credits (auto off)Cost
Short chat turn1.11.2$0.01
Daily coding request2.12.3$0.02
Agent session step7.17.9$0.07

At about 2.1 credits per daily-coding request, Gemini 3.5 Flash ranks #11 of 22 current models by cost, about 7.3x the cheapest (GPT-5.4 nano).

Requests per plan allowance

Daily-coding requests the included monthly credits buy, before any overage.

PlanCredits / monthRequests
Copilot Pro1,500712
Copilot Pro+7,0003,323
Copilot Max20,0009,496
Copilot Business1,900902
Copilot Enterprise3,9001,851

Copilot rate vs direct API

GitHub Copilot bills Gemini 3.5 Flash at $1.50 in / $9.00 out per 1M. That input rate is the same as the direct Google gemini-3.5-flash API price of $1.50 in / $9.00 out (validated 2026-06-15).

Estimate your monthly burn with Gemini 3.5 Flash

Cheaper: Gemini 2.5 Pro - Pricier: Claude Sonnet 5

All models - GitHub AI Credits