Verified 2025-11-26 · sourced from Google
Gemini 3 Pro Preview Token Calculator & Cost Guide
Estimate Google Gemini 3 Pro Preview API usage in dollars before you send a single request. Standard pricing is $2.00 per million input tokens and $12.00 per million output tokens with a 2M token context window.
Context window
2,000,000 tokens
Input price
$2.00 / 1M
Output price
$12.00 / 1M
Cached input
$0.200 / 1M
Usage scenarios
Compare standard and cached pricing (where available) across common workloads.
| Scenario | Tokens in | Tokens out | Total tokens | Standard cost | Cached cost |
|---|---|---|---|---|---|
Quick chat reply Single user question with a short assistant answer | 650 | 220 | 870 | $0.0039 | $0.0028 |
Coding assistant session Multi-turn pair programming exchange (≈6 turns) | 2,600 | 1,400 | 4,000 | $0.0220 | $0.0173 |
Knowledge base response Retrieval-augmented answer referencing multiple passages | 12,000 | 3,000 | 15,000 | $0.0600 | $0.0384 |
Near-max context run Large document processing approaching the 2M token limit | 1,760,000 | 240,000 | 2,000,000 | $6.40 | $3.23 |
Daily & monthly budgeting
Translate usage into predictable operating expenses across popular deployment sizes.
| Profile | Requests/day | Tokens/day | Daily cost | Monthly cost | Cached daily | Cached monthly |
|---|---|---|---|---|---|---|
| Team pilot | 25 | 75,000 | $0.400 | $12.00 | $0.310 | $9.30 |
| Product launch | 100 | 500,000 | $2.50 | $75.00 | $1.87 | $56.10 |
| Enterprise scale | 500 | 3,000,000 | $16.00 | $480.00 | $12.40 | $372.00 |
Pricing notes
- 🆕 Latest Gemini model (Nov 2025 release)
- Standard tier (≤ 200K tokens): input $2.00/MTok, output $12.00/MTok
- Long context (> 200K tokens): input $4.00/MTok, output $18.00/MTok
- Context caching (≤ 200K): $0.20/MTok, storage $4.50/MTok per hour
- Context caching (> 200K): $0.40/MTok, storage $4.50/MTok per hour
- Batch tier: 50% discount - input $1.00/MTok (≤200K) or $2.00/MTok (>200K)
- Batch output: $6.00/MTok (≤200K) or $9.00/MTok (>200K)
Frequently asked questions
How much does Gemini 3 Pro Preview cost per 1,000 tokens?
At the published rates of $2.00 per million input tokens and $12.00 per million output tokens, a typical 1,000 token request (≈70% input, 30% output) costs about $0.0050.
Does Gemini 3 Pro Preview offer cached input discounts?
Gemini 3 Pro Preview drops input costs to $0.200 per million cached tokens. Using cached contexts, that same 1,000 token call totals $0.0037, a significant saving for chatbots and RAG systems.
What is the context window for Gemini 3 Pro Preview?
Gemini 3 Pro Preview supports up to 2,000,000 tokens (2M), allowing large prompts and retrieval-augmented payloads in a single call.
How fresh is the Gemini 3 Pro Preview pricing data?
Pricing is sourced from https://ai.google.dev/gemini-api/docs/pricing and was last verified on 2025-11-26. The calculator updates automatically when models.json is refreshed.