gpt-oss-20b is 7.9× cheaper per million tokens (blended). DeepSeek V3.1 Terminus has the larger context window (163,840 vs 131,072 tokens).
DeepSeek V3.1 Terminus vs gpt-oss-20b
Live catalog fields. Best-in-row is highlighted.
DeepSeek V3.1 Terminusopen
DeepSeek · deepseek__deepseek-v3.1-terminus
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Identity
| Field | deepseek__deepseek-v3.1-terminus | openai__gpt-oss-20b |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Slug | deepseek__deepseek-v3.1-terminus | openai__gpt-oss-20b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | deepseek-ai/DeepSeek-V3.1-Terminus | openai/gpt-oss-20b |
Quality
| Field | deepseek__deepseek-v3.1-terminus | openai__gpt-oss-20b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | deepseek__deepseek-v3.1-terminus | openai__gpt-oss-20b |
|---|---|---|
| Input $ / 1M tokens | $0.27 | $0.03 |
| Cached input $ / 1M | — | $0.03 |
| Output $ / 1M tokens | $1.00 | $0.13 |
Context
| Field | deepseek__deepseek-v3.1-terminus | openai__gpt-oss-20b |
|---|---|---|
| Max context tokens | 163,840 | 131,072 |
| Max output tokens | 147,456 | 117,964 |
Modalities
| Field | deepseek__deepseek-v3.1-terminus | openai__gpt-oss-20b |
|---|---|---|
| Input | text | text |
| Output | text | text |