DeepSeek V4 Flash 0423 is 10.3× cheaper per million tokens (blended). Gemini 2.5 Flash has the larger context window (1,048,576 vs 1,048,575 tokens). DeepSeek V4 Flash 0423 is open-weights; the other is not.
DeepSeek V4 Flash 0423 vs Gemini 2.5 Flash
Live catalog fields. Best-in-row is highlighted.
DeepSeek V4 Flash 0423open
DeepSeek · deepseek__deepseek-v4-flash
Gemini 2.5 Flash
Google · google__gemini-2.5-flash
Identity
| Field | deepseek__deepseek-v4-flash | google__gemini-2.5-flash |
|---|---|---|
| Provider | DeepSeek | |
| Slug | deepseek__deepseek-v4-flash | google__gemini-2.5-flash |
| Status | live | live |
| Open weights | Yes | No |
| License | — | — |
| HuggingFace | deepseek-ai/DeepSeek-V4-Flash | — |
Quality
| Field | deepseek__deepseek-v4-flash | google__gemini-2.5-flash |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | deepseek__deepseek-v4-flash | google__gemini-2.5-flash |
|---|---|---|
| Input $ / 1M tokens | $0.09 | $0.30 |
| Cached input $ / 1M | $0.02 | $0.03 |
| Output $ / 1M tokens | $0.18 | $2.50 |
Context
| Field | deepseek__deepseek-v4-flash | google__gemini-2.5-flash |
|---|---|---|
| Max context tokens | 1,048,575 | 1,048,576 |
| Max output tokens | 943,717 | 65,535 |
Modalities
| Field | deepseek__deepseek-v4-flash | google__gemini-2.5-flash |
|---|---|---|
| Input | text | file, image, text, audio, video |
| Output | text | text |