Compare
2–4 model comparison. Best-in-row is highlighted.
DeepSeek V4 Pro 0423open
DeepSeek · deepseek__deepseek-v4-pro
Gemini 3.8 Flash
Google · google__gemini-3.8-flash
Identity
| Field | deepseek__deepseek-v4-pro | google__gemini-3.8-flash |
|---|---|---|
| Provider | DeepSeek | |
| Slug | deepseek__deepseek-v4-pro | google__gemini-3.8-flash |
| Status | live | live |
| Open weights | Yes | No |
| License | — | — |
| HuggingFace | deepseek-ai/DeepSeek-V4-Pro | — |
Quality
| Field | deepseek__deepseek-v4-pro | google__gemini-3.8-flash |
|---|---|---|
| Quality index (0–100) | 88.2 | 87.1 |
Cost
| Field | deepseek__deepseek-v4-pro | google__gemini-3.8-flash |
|---|---|---|
| Input $ / 1M tokens | $0.72 | $0.75 |
| Cached input $ / 1M | $0.06 | $0.07 |
| Output $ / 1M tokens | $1.44 | $3.75 |
Context
| Field | deepseek__deepseek-v4-pro | google__gemini-3.8-flash |
|---|---|---|
| Max context tokens | 1,024,000 | 1,048,576 |
| Max output tokens | 384,000 | 65,536 |
Modalities
| Field | deepseek__deepseek-v4-pro | google__gemini-3.8-flash |
|---|---|---|
| Input | text | text, image, video, file, audio |
| Output | text | text |