gpt-oss-20b is 5.0× cheaper per million tokens (blended). DeepSeek V4.1 Flash has the larger context window (1,048,576 vs 131,072 tokens, 8.0×).
DeepSeek V4.1 Flash vs gpt-oss-20b
Live catalog fields. Best-in-row is highlighted.
DeepSeek V4.1 Flashopen
DeepSeek · deepseek__deepseek-v4.1-flash
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Identity
| Field | deepseek__deepseek-v4.1-flash | openai__gpt-oss-20b |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Slug | deepseek__deepseek-v4.1-flash | openai__gpt-oss-20b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | deepseek-ai/DeepSeek-V4.1-Flash | openai/gpt-oss-20b |
Quality
| Field | deepseek__deepseek-v4.1-flash | openai__gpt-oss-20b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | deepseek__deepseek-v4.1-flash | openai__gpt-oss-20b |
|---|---|---|
| Input $ / 1M tokens | $0.04 | $0.02 |
| Cached input $ / 1M | $0.02 | $0.01 |
| Output $ / 1M tokens | $0.50 | $0.09 |
Context
| Field | deepseek__deepseek-v4.1-flash | openai__gpt-oss-20b |
|---|---|---|
| Max context tokens | 1,048,576 | 131,072 |
| Max output tokens | 943,718 | 32,768 |
Modalities
| Field | deepseek__deepseek-v4.1-flash | openai__gpt-oss-20b |
|---|---|---|
| Input | text, image | text |
| Output | text | text |