Model comparison
Gemini 2.5 Flash vs DeepSeek R1
Gemini 2.5 Flash
Cheap multimodal at million-token scale.
DeepSeek
DeepSeek R1
The open-weights reasoning model that reset the cost curve.
Specs
| Metric | Gemini 2.5 Flash | DeepSeek R1 |
|---|---|---|
| Context window | 1.0M tokens↑ | 64K tokens |
| Input $/1M tokens | $0.300↑ | $0.700 |
| Output $/1M tokens | $2.50↑ | $2.50 |
| Modalities | File · Image · Text · Audio · Video | Text |
| Open weights | No | Yes |
| Released | - | Jan 2025 |
Capability differences
| Capability | Gemini 2.5 Flash | DeepSeek R1 |
|---|---|---|
| Tool use | Yes | No |
| Vision | Yes | No |
| Prompt caching | Yes | No |
| Open weights | No | Yes |
Key differences
- -Gemini 2.5 Flash offers 1.0M context; DeepSeek R1 offers 64K.
- -Input pricing: Gemini 2.5 Flash at $0.300/1M vs DeepSeek R1 at $0.700/1M.
- -DeepSeek R1 is open weights; Gemini 2.5 Flash is proprietary.