Gemini API pricing
Gemini API prices per million tokens, context windows and independent benchmark scores, plus preview models that are not on an API yet.
Prices updated . Benchmarks updated .
Prices are the current OpenRouter rate, refreshed about hourly. This page does not chart older prices.
| Model | You send / 1M | It replies / 1M | Context | ECI | Launched |
|---|---|---|---|---|---|
| Gemini 4 ArgonClosed | $2.00 | $10.00 | 1.05M | 166.1 | 2026-10-13 |
| Gemini 3.7 FlashClosed | $0.750 | $3.75 | 1.05M | 158.2 | 2026-08-13 |
| Gemini 3.8 FlashClosed | $0.825 | $4.13 | 1.05M | 157.6 | 2026-09-02 |
| Gemini 3.1 Pro PreviewClosed | $2.00 | $12.00 | 1.05M | 155.2 | 2026-02-19 |
| Gemini 3.5 FlashClosed | $1.50 | $9.00 | 1.05M | 155.0 | 2026-05-19 |
| Gemini 3.6 FlashClosed | $0.750 | $3.75 | 1.05M | 154.7 | 2026-07-21 |
| Gemini 3 Flash PreviewClosed | $0.500 | $3.00 | 1.05M | 152.0 | 2025-12-17 |
| Gemini 3.5 Flash LiteClosed | $0.300 | $2.50 | 1.05M | 145.0 | 2026-07-21 |
| Gemini 3.1 Flash LiteClosed | $0.250 | $1.50 | 1.05M | 144.3 | 2026-05-07 |
| Gemma 4 31BOpen weights | $0.200 | $0.400 | 262K | 143.1 | 2026-04-02 |
| Gemma 4 26B A4B Open weights | $0.068 | $0.225 | 262K | 141.9 | 2026-04-02 |
| Gemma 3 27BOpen weights | $0.080 | $0.350 | 131K | 129.9 | 2025-03-12 |
| Gemma 3 12BOpen weights | $0.050 | $0.150 | 131K | 123.5 | 2025-03-12 |
| Gemma 2 27BOpen weights | $0.650 | $0.650 | 8K | 122.1 | 2024-07-13 |
| Gemma 3 4BOpen weights | $0.050 | $0.100 | 131K | 115.8 | 2025-03-12 |
| Gemini 4 CarbonPreviewClosed | TBA | TBA | TBA | n/a | 2026-10-28 |
| Nano Banana 2.1Closed | $1.50 | $7.50 | 131K | n/a | 2026-10-06 |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Closed | $0.250 | $1.50 | 66K | n/a | 2026-06-30 |
| Nano Banana 2 (Gemini 3.1 Flash Image)Closed | $0.500 | $3.00 | 131K | n/a | 2026-05-28 |
| Nano Banana Pro (Gemini 3 Pro Image)Closed | $2.00 | $12.00 | 66K | n/a | 2026-05-28 |
| Lyria 3 Pro PreviewClosed | Free | Free | 1.05M | n/a | 2026-03-25 |
| Lyria 3 Clip PreviewClosed | Free | Free | 1.05M | n/a | 2026-03-25 |
| Gemini 3.1 Flash Lite PreviewClosed | $0.250 | $1.50 | 1.05M | n/a | 2026-03-03 |
| Nano Banana 2 (Gemini 3.1 Flash Image Preview)Closed | $0.500 | $3.00 | 131K | n/a | 2026-02-26 |
| Gemini 3.1 Pro Preview Custom ToolsClosed | $2.00 | $12.00 | 1.05M | n/a | 2026-02-19 |
| Nano Banana Pro (Gemini 3 Pro Image Preview)Closed | $2.00 | $12.00 | 33K | n/a | 2025-11-20 |
| Nano Banana (Gemini 2.5 Flash Image)Closed | $0.300 | $2.50 | 33K | n/a | 2025-08-26 |
| Gemini 2.5 Flash LiteClosed | $0.100 | $0.400 | 1.05M | n/a | 2025-06-17 |
| Gemini 2.5 FlashClosed | $0.300 | $2.50 | 1.05M | n/a | 2025-06-17 |
| Gemini 2.5 ProClosed | $1.25 | $10.00 | 1.05M | n/a | 2025-06-17 |
| Gemini 2.5 Pro Preview 06-05Closed | $1.25 | $10.00 | 1.05M | n/a | 2025-06-05 |
Which Google model ranks highest?
Gemini 4 Argon has the highest Epoch Capabilities Index among Google models on this page, at 166.1. Gemini 3.7 Flash is next at 158.2. Gemini 4 Argon costs $10.00 per million output tokens and reads 1.05M of context. The index is an independent score from Epoch AI. Lab-reported numbers are kept off this ranking.
Which Google model is cheapest?
Lyria 3 Pro Preview has the lowest published output price among Google models here, at Free per million tokens. Input tokens cost Free per million and the context window is 1.05M. Lyria 3 Clip Preview is next at Free per million output tokens. It has no published Epoch Capabilities Index in the current file.
Which Google open-weight models lead?
Gemma 4 31B leads Google open-weight models that have a published Epoch Capabilities Index, at 143.1. It is from Google, costs $0.400 per million output tokens, and reads 262K. Gemma 4 26B A4B from Google follows at 141.9. Open weights means the lab published the weights. The license on the model page says what you can do with them.
FAQ
Which Google model ranks highest?
Gemini 4 Argon has the highest Epoch Capabilities Index among Google models on this page, at 166.1. Gemini 3.7 Flash is next at 158.2. Gemini 4 Argon costs $10.00 per million output tokens and reads 1.05M of context. The index is an independent score from Epoch AI. Lab-reported numbers are kept off this ranking.
Which Google model is cheapest?
Lyria 3 Pro Preview has the lowest published output price among Google models here, at Free per million tokens. Input tokens cost Free per million and the context window is 1.05M. Lyria 3 Clip Preview is next at Free per million output tokens. It has no published Epoch Capabilities Index in the current file.
How many Google models are listed?
This page lists 31 Google models with a public price or an independent score. Open the comparison table to filter the full catalogue.
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.