DeepSeek V4 Flash 0423 is 142.5× cheaper per million tokens (blended). DeepSeek V4 Flash 0423 leads quality index by 6.2 points (88.0 vs 81.8). GPT-5.5 has the larger context window (1,050,000 vs 1,024,000 tokens). DeepSeek V4 Flash 0423 is open-weights; the other is not.
DeepSeek V4 Flash 0423 vs GPT-5.5
Live catalog fields. Best-in-row is highlighted.
DeepSeek V4 Flash 0423open
DeepSeek · deepseek__deepseek-v4-flash
GPT-5.5
OpenAI · openai__gpt-5.5
Identity
| Field | deepseek__deepseek-v4-flash | openai__gpt-5.5 |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Slug | deepseek__deepseek-v4-flash | openai__gpt-5.5 |
| Status | live | live |
| Open weights | Yes | No |
| License | — | — |
| HuggingFace | deepseek-ai/DeepSeek-V4-Flash | — |
Quality
| Field | deepseek__deepseek-v4-flash | openai__gpt-5.5 |
|---|---|---|
| Quality index (0–100) | 88.0 | 81.8 |
Cost
| Field | deepseek__deepseek-v4-flash | openai__gpt-5.5 |
|---|---|---|
| Input $ / 1M tokens | $0.08 | $5.00 |
| Cached input $ / 1M | $0.02 | $0.50 |
| Output $ / 1M tokens | $0.16 | $30.00 |
Context
| Field | deepseek__deepseek-v4-flash | openai__gpt-5.5 |
|---|---|---|
| Max context tokens | 1,024,000 | 1,050,000 |
| Max output tokens | 384,000 | 128,000 |
Modalities
| Field | deepseek__deepseek-v4-flash | openai__gpt-5.5 |
|---|---|---|
| Input | text | file, image, text |
| Output | text | text |