# DeepSeek vs Gemini API pricing, compared model by model

On 25 September 2026 the cheapest DeepSeek model costs $0.0482 per million input tokens against $0.05 for the cheapest Gemini model, and the typical DeepSeek model is the cheaper of the two.

Prices checked 25 September 2026 at 06.00 UTC . Source OpenRouter public model list . US dollars per million tokens

## At a glance

|  | DeepSeek (DeepSeek) | Gemini (Google) |
|---|---|---|
| Models listed | 15 | 26 |
| Cheapest model | DeepSeek V4 Flash 0423, $0.0482 in, $0.0963 out | Gemma 3 4B, $0.05 in, $0.10 out |
| Most expensive model | R1, $0.70 in, $2.50 out | Nano Banana Pro (Gemini 3 Pro Image), $2.00 in, $12.00 out |
| Median input price | $0.27 | $0.50 |
| Median output price | $0.89 | $2.75 |
| Largest context | 1.31072M, DeepSeek V4 Flash 0731 | 1.04858M, Gemini 3.8 Flash |
| Newest model | DeepSeek V4.1 Flash, 2026-09-10 | Gemini 3.8 Flash, 2026-09-02 |
| Models with a batch price | 1 | 11 |

## Every model, with your monthly cost

Input tokens per call

Output tokens per call

Calls a day

Search models

| Model | Provider | Input | Output | Cached input | Batch in / out | Context | Your month | Listed |
|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | DeepSeek | $0.075 | $0.30 | $0.0015 | $0.112 / $0.336 | 1.04858M | $9.00 | 2026-09-10 |
| Gemini 3.8 Flash | Google | $0.75 | $3.75 | $0.075 | $0.375 / $1.88 | 1.04858M | $101.25 | 2026-09-02 |
| DeepSeek V4 Flash Vision Exp | DeepSeek | $0.22 | $0.66 | $0.007 |  | 1.04858M | $23.10 | 2026-08-21 |
| Gemini 3.7 Flash | Google | $0.75 | $3.75 | $0.075 | $0.375 / $1.88 | 1.04858M | $101.25 | 2026-08-13 |
| DeepSeek V4 Pro 0813 | DeepSeek | $0.3458 | $1.04 | $0.0115 |  | 1.04858M | $36.31 | 2026-08-12 |
| DeepSeek V4 Flash 0731 | DeepSeek | $0.03 | $0.32 | $0.016 |  | 1.31072M | $6.60 | 2026-07-31 |
| Gemini 3.6 Flash | Google | $0.75 | $3.75 | $0.075 | $0.375 / $1.88 | 1.04858M | $101.25 | 2026-07-21 |
| Gemini 3.5 Flash Lite | Google | $0.30 | $2.50 | $0.03 | $0.15 / $1.25 | 1.04858M | $55.50 | 2026-07-21 |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | Google | $0.25 | $1.50 |  |  | 66K | $37.50 | 2026-06-30 |
| Nano Banana 2 (Gemini 3.1 Flash Image) | Google | $0.50 | $3.00 |  |  | 131K | $75.00 | 2026-06-18 |
| Nano Banana Pro (Gemini 3 Pro Image) | Google | $2.00 | $12.00 | $0.20 |  | 131K | $300.00 | 2026-06-18 |
| Gemini 3.5 Flash | Google | $1.50 | $9.00 | $0.15 | $0.75 / $4.50 | 1.04858M | $225.00 | 2026-05-19 |
| Gemini 3.1 Flash Lite | Google | $0.25 | $1.50 | $0.025 | $0.125 / $0.75 | 1.04858M | $37.50 | 2026-05-07 |
| DeepSeek V4 Pro 0423 | DeepSeek | $0.7129 | $1.43 | $0.0594 |  | 1.04858M | $64.16 | 2026-04-24 |
| DeepSeek V4 Flash 0423 | DeepSeek | $0.0482 | $0.0963 | $0.0096 |  | 1.04858M | $4.33 | 2026-04-24 |
| Gemma 4 26B A4B free tier on OpenRouter | Google | $0.0675 | $0.225 | $0.0375 |  | 262K | $7.42 | 2026-04-03 |
| Gemma 4 31B free tier on OpenRouter | Google | $0.09 | $0.34 | $0.05 |  | 262K | $10.50 | 2026-04-02 |
| Gemini 3.1 Flash Lite Preview | Google | $0.25 | $1.50 | $0.025 |  | 1.04858M | $37.50 | 2026-03-03 |
| Nano Banana 2 (Gemini 3.1 Flash Image Preview) | Google | $0.50 | $3.00 |  |  | 66K | $75.00 | 2026-02-26 |
| Gemini 3.1 Pro Preview Custom Tools | Google | $2.00 | $12.00 | $0.20 |  | 1.04858M | $300.00 | 2026-02-25 |
| Gemini 3.1 Pro Preview | Google | $2.00 | $12.00 | $0.20 | $1.00 / $6.00 | 1.04858M | $300.00 | 2026-02-19 |
| Gemini 3 Flash Preview | Google | $0.50 | $3.00 | $0.05 | $0.25 / $1.50 | 1.04858M | $75.00 | 2025-12-17 |
| DeepSeek V3.2 retiring 2026-09-28 | DeepSeek | $0.269 | $0.40 | $0.1345 |  | 164K | $22.14 | 2025-12-01 |
| Nano Banana Pro (Gemini 3 Pro Image Preview) | Google | $2.00 | $12.00 | $0.20 |  | 66K | $300.00 | 2025-11-20 |
| Nano Banana (Gemini 2.5 Flash Image) | Google | $0.30 | $2.50 | $0.03 |  | 33K | $55.50 | 2025-10-07 |
| DeepSeek V3.2 Exp retiring 2026-09-28 | DeepSeek | $0.27 | $0.41 |  |  | 164K | $22.35 | 2025-09-29 |
| DeepSeek V3.1 Terminus retiring 2026-09-28 | DeepSeek | $0.27 | $1.00 | $0.135 |  | 164K | $31.20 | 2025-09-22 |
| DeepSeek V3.1 | DeepSeek | $0.25 | $0.95 | $0.13 |  | 164K | $29.25 | 2025-08-21 |
| Gemini 2.5 Flash Lite retiring 2026-10-20 | Google | $0.10 | $0.40 | $0.01 | $0.05 / $0.20 | 1.04858M | $12.00 | 2025-07-22 |
| Gemini 2.5 Flash retiring 2026-10-20 | Google | $0.30 | $2.50 | $0.03 | $0.15 / $1.25 | 1.04858M | $55.50 | 2025-06-17 |
| Gemini 2.5 Pro retiring 2026-10-20 | Google | $1.25 | $10.00 | $0.125 | $0.625 / $5.00 | 1.04858M | $225.00 | 2025-06-17 |
| Gemini 2.5 Pro Preview 06-05 | Google | $1.25 | $10.00 | $0.125 |  | 1.04858M | $225.00 | 2025-06-05 |
| R1 0528 | DeepSeek | $0.50 | $2.15 | $0.35 |  | 164K | $62.25 | 2025-05-28 |
| DeepSeek V3 0324 | DeepSeek | $0.25 | $1.00 |  |  | 164K | $30.00 | 2025-03-24 |
| Gemma 3 4B | Google | $0.05 | $0.10 |  |  | 131K | $4.50 | 2025-03-13 |
| Gemma 3 12B | Google | $0.05 | $0.15 |  |  | 131K | $5.25 | 2025-03-13 |
| Gemma 3 27B | Google | $0.08 | $0.45 | $0.04 |  | 131K | $11.55 | 2025-03-12 |
| R1 Distill Llama 70B retiring 2026-09-28 | DeepSeek | $0.80 | $0.80 |  |  | 8K | $60.00 | 2025-01-23 |
| R1 | DeepSeek | $0.70 | $2.50 |  |  | 64K | $79.50 | 2025-01-20 |
| DeepSeek V3 | DeepSeek | $0.32 | $0.89 |  |  | 164K | $32.55 | 2024-12-26 |
| Gemma 2 27B | Google | $0.65 | $0.65 |  |  | 8K | $48.75 | 2024-07-13 |

[All DeepSeek prices](https://shurco.ai/tools/llm-api-pricing/deepseek/) . [All Gemini prices](https://shurco.ai/tools/llm-api-pricing/google/) . [Every provider](https://shurco.ai/tools/llm-api-pricing/)

## Common questions

### Is DeepSeek cheaper than Gemini?

On 25 September 2026, the median DeepSeek model on this list costs $0.27 per million input tokens and $0.89 per million output tokens, against $0.50 and $2.75 for Gemini. By that measure DeepSeek is cheaper, but compare the specific models you would use, since both providers sell models at very different price points.

### What is the cheapest DeepSeek model compared with the cheapest Gemini model?

The cheapest DeepSeek model is DeepSeek V4 Flash 0423 at $0.0482 in and $0.0963 out per million tokens. The cheapest Gemini model is Gemma 3 4B at $0.05 in and $0.10 out.

### Which has the larger context window, DeepSeek or Gemini?

The largest DeepSeek context on this list is 1.31072M tokens (DeepSeek V4 Flash 0731) and the largest Gemini context is 1.04858M tokens (Gemini 3.8 Flash).

### How should I choose between DeepSeek and Gemini for a production agent?

Price per token is one input. Run both on a set of your own real cases, count how often each needs a retry or a human check, and compare the total cost of a correct answer rather than the cost of a token.

## Choosing a model for a production agent

Price is one input. Quality on your own cases, latency and the cost of retries decide the rest. [Tell me what you are building.](https://shurco.ai/#contact)

Web version https://shurco.ai/tools/llm-api-pricing/compare/deepseek-vs-gemini/