Current price verification is unresolved or overdue. These are the last recorded rates; check the official source before budgeting. We do not relabel an old check with today's build date.
Gemini 3.1 Pro API Pricing
Gemini 3.1 Pro costs $2.00 per 1M input tokens and $12.00 per 1M output tokens. These rates were last verified on .
Published rates and billing units
| Billing dimension | USD list price |
|---|---|
| Input / 1M tokens | $2.00 |
| Cached input / 1M tokens | $0.20 |
| Requests above 200,000 input tokens: Input / 1M tokens | $4.00 |
| Requests above 200,000 input tokens: Cached input / 1M tokens | $0.40 |
| Requests above 200,000 input tokens: Output / 1M tokens | $18.00 |
| Output / 1M tokens | $12.00 |
Verified 2026-11-02 · Official source · Pricing methodology. Taxes, optional services and account-specific discounts are not included.
Cost examples
These examples use published list prices only. They exclude taxes, enterprise discounts, minimum charges, retries, batch discounts, and provider-specific billing rules.
1M input + 1M output
$22.00
A direct per-million comparison against every other text model.
100K input + 25K output
$0.50
A compact chat, summarization, or analysis workload.
10M input + 2M output
$76.00
A monthly production estimate for heavier RAG or agent traffic.
75% cached input + 250K output
$5.80
Cached input is about 90% cheaper than standard input at list price.
Calculator for Gemini 3.1 Pro
Enter your own input, output, and cached-token assumptions. This calculator is preloaded with only Gemini 3.1 Pro, so the result stays focused on this model.
Input cost
$4.00
Output cost
$18.00
Total
$22.00
Long-context rates apply because this request exceeds 200,000 input tokens.
Price history
No list-price movement across 209 daily snapshots from 2026-04-16 to 2026-11-11.
When to use Gemini 3.1 Pro
Good fit
- reasoning-heavy prompts, planning, analysis, and multi-step tool use
- high-volume routing, classification, extraction, summaries, and fallback traffic
- long-document and repository-scale prompts where context window matters
Be careful with
- blind migration without testing your own prompts, latency, and failure modes