gpt-oss-20b is 6.5× cheaper per million tokens (blended). Qwen-Plus has the larger context window (1,000,000 vs 131,072 tokens, 7.6×). gpt-oss-20b is open-weights; the other is not.
gpt-oss-20b vs Qwen-Plus
Live catalog fields. Best-in-row is highlighted.
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Qwen-Plus
Qwen · qwen__qwen-plus
Identity
| Field | openai__gpt-oss-20b | qwen__qwen-plus |
|---|---|---|
| Provider | OpenAI | Qwen |
| Slug | openai__gpt-oss-20b | qwen__qwen-plus |
| Status | live | live |
| Open weights | Yes | No |
| License | — | — |
| HuggingFace | openai/gpt-oss-20b | — |
Quality
| Field | openai__gpt-oss-20b | qwen__qwen-plus |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-20b | qwen__qwen-plus |
|---|---|---|
| Input $ / 1M tokens | $0.03 | $0.26 |
| Cached input $ / 1M | $0.03 | $0.05 |
| Output $ / 1M tokens | $0.13 | $0.78 |
Context
| Field | openai__gpt-oss-20b | qwen__qwen-plus |
|---|---|---|
| Max context tokens | 131,072 | 1,000,000 |
| Max output tokens | 117,964 | 32,768 |
Modalities
| Field | openai__gpt-oss-20b | qwen__qwen-plus |
|---|---|---|
| Input | text | text |
| Output | text | text |