Google · October 2026
Gemini API pricing, every model
28 Gemini models, from $0.05 to $2 per million input tokens. Gemini Flash, Pro and the image models, plus open Gemma.
Prices from OpenRouter’s models API, updated October 29, 2026
Gemma 3 4B
$0.05 in · $0.10 outAbout $3.45 a month for a 1,000-chats-a-day support bot.
Gemini 4 Argon
$2 in · $10 outReleased 2026-10-13, 1.05M tokens of context.
Gemini 4 Argon
−95%Cached input costs $0.10 instead of $2 per 1M tokens.
All Gemini models and prices
| Model | Released | Input /1M | Output /1M | Cache read /1M | Batch in / out | Context | Chatbot, per month* |
|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | 2026-10-13 | $2 | $10 | $0.10 | $1 / $5 | 1.05M | $210 |
| Nano Banana 2.1 | 2026-10-06 | $1.50 | $7.50 | – | – | 66K | $158 |
| Gemini 3.8 Flash | 2026-09-02 | $0.825 | $4.13 | $0.083 | $0.375 / $1.88 | 1.05M | $86.62 |
| Gemini 3.7 Flash | 2026-08-13 | $0.75 | $3.75 | $0.075 | $0.375 / $1.88 | 1.05M | $78.75 |
| Gemini 3.5 Flash Lite | 2026-07-21 | $0.30 | $2.50 | $0.03 | $0.15 / $1.25 | 1.05M | $43.50 |
| Gemini 3.6 Flash | 2026-07-21 | $0.75 | $3.75 | $0.075 | $0.375 / $1.88 | 1.05M | $78.75 |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | 2026-06-30 | $0.25 | $1.50 | – | – | 66K | $29.25 |
| Nano Banana Pro (Gemini 3 Pro Image) | 2026-06-18 | $2 | $12 | $0.20 | – | 131K | $234 |
| Nano Banana 2 (Gemini 3.1 Flash Image) | 2026-06-18 | $0.50 | $3 | – | – | 131K | $58.50 |
| Gemini 3.5 Flash | 2026-05-19 | $1.50 | $9 | $0.15 | $0.75 / $4.50 | 1.05M | $176 |
| Gemini 3.1 Flash Lite | 2026-05-07 | $0.25 | $1.50 | $0.025 | $0.125 / $0.75 | 1.05M | $29.25 |
| Gemma 4 26B A4B free variant | 2026-04-03 | $0.076 | $0.255 | $0.043 | – | 262K | $6.50 |
| Gemma 4 31B free variant | 2026-04-02 | $0.20 | $0.40 | – | – | 262K | $13.80 |
| Gemini 3.1 Flash Lite Preview | 2026-03-03 | $0.25 | $1.50 | $0.025 | – | 1.05M | $29.25 |
| Nano Banana 2 (Gemini 3.1 Flash Image Preview) | 2026-02-26 | $0.50 | $3 | – | – | 66K | $58.50 |
| Gemini 3.1 Pro Preview Custom Tools | 2026-02-25 | $2 | $12 | $0.20 | – | 1.05M | $234 |
| Gemini 3.1 Pro Preview | 2026-02-19 | $2 | $12 | $0.20 | $1 / $6 | 1.05M | $234 |
| Gemini 3 Flash Preview | 2025-12-17 | $0.50 | $3 | $0.05 | $0.25 / $1.50 | 1.05M | $58.50 |
| Nano Banana Pro (Gemini 3 Pro Image Preview) | 2025-11-20 | $2 | $12 | $0.20 | – | 66K | $234 |
| Nano Banana (Gemini 2.5 Flash Image) | 2025-10-07 | $0.30 | $2.50 | $0.03 | – | 33K | $43.50 |
| Gemini 2.5 Flash Lite | 2025-07-22 | $0.10 | $0.40 | $0.01 | – | 1.05M | $9.30 |
| Gemini 2.5 Flash | 2025-06-17 | $0.30 | $2.50 | $0.03 | – | 1.05M | $43.50 |
| Gemini 2.5 Pro | 2025-06-17 | $1.25 | $10 | $0.125 | – | 1.05M | $176 |
| Gemini 2.5 Pro Preview 06-05 | 2025-06-05 | $1.25 | $10 | $0.125 | – | 1.05M | $176 |
| Gemma 3 12B | 2025-03-13 | $0.05 | $0.15 | – | – | 131K | $4.05 |
| Gemma 3 4B | 2025-03-13 | $0.05 | $0.10 | – | – | 131K | $3.45 |
| Gemma 3 27B | 2025-03-12 | $0.08 | $0.35 | $0.04 | – | 131K | $7.80 |
| Gemma 2 27B | 2024-07-13 | $0.65 | $0.65 | – | – | 8K | $37.05 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
What three real workloads cost a month
| Model | Support chatbot | Daily summaries | Coding agent |
|---|---|---|---|
| Gemma 3 4B | $3.45 | $54.00 | $38.40 |
| Gemma 3 12B | $4.05 | $58.50 | $39.60 |
| Gemma 4 26B A4B | $6.50 | $91.80 | $41.62 |
| Gemma 3 27B | $7.80 | $103 | $42.96 |
| Gemini 2.5 Flash Lite | $9.30 | $126 | $29.76 |
| Gemma 4 31B | $13.80 | $216 | $154 |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | $29.25 | $360 | $216 |
| Gemini 3.1 Flash Lite | $29.25 | $360 | $86.40 |
Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out · Daily summaries: 10,000 a day, 3,000 tokens in, 300 out · Coding agent: 400 calls a day, 60,000 tokens in (80% cached), 2,000 out. Cached share billed at the cache-read price where the model has one.
Compare with other providers
Gemini pricing questions
How much does the Gemini API cost?
Google’s models range from $0.05 per 1M input tokens and $0.10 per 1M output tokens (Gemma 3 4B) to $2 and $12 (Nano Banana Pro (Gemini 3 Pro Image Preview)). The newest, Gemini 4 Argon, costs $2 in and $10 out.
Which Gemini model is the cheapest?
Gemma 3 4B, at $0.05 per 1M input tokens. A support chatbot doing 1,000 chats a day would cost about $3.45 a month on it.
Does Google discount cached prompts?
Yes. On Gemini 4 Argon, cached input costs $0.10 per 1M tokens instead of $2, 95% less. Long, repeated system prompts and agent loops benefit most.
Is there a batch discount?
9 Gemini models have a batch price, typically half the normal rate, for jobs that can wait (up to 24 hours). See the Batch column below.
How do I track my Gemini spend per product?
Route it through OpenRouter with one API key per product and connect OpenRouter to Glow: you get spend by model, API key and product every day, with cache hit rate. Track AI spend.
See your real Gemini bill.
Glow shows what you actually spend by model, API key and product, every day, and which cheaper model would do the same job.
- Read-only keys
- Never shown again
- 2FA + Face ID
- 7-day trial