gpt-oss-20b is 14.6× cheaper per million tokens (blended). Qwen3.5-122B-A10B has the larger context window (262,144 vs 131,072 tokens, 2.0×).
gpt-oss-20b vs Qwen3.5-122B-A10B
Live catalog fields. Best-in-row is highlighted.
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Qwen3.5-122B-A10Bopen
Qwen · qwen__qwen3.5-122b-a10b
Identity
| Field | openai__gpt-oss-20b | qwen__qwen3.5-122b-a10b |
|---|---|---|
| Provider | OpenAI | Qwen |
| Slug | openai__gpt-oss-20b | qwen__qwen3.5-122b-a10b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | openai/gpt-oss-20b | Qwen/Qwen3.5-122B-A10B |
Quality
| Field | openai__gpt-oss-20b | qwen__qwen3.5-122b-a10b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-20b | qwen__qwen3.5-122b-a10b |
|---|---|---|
| Input $ / 1M tokens | $0.03 | $0.26 |
| Cached input $ / 1M | $0.03 | — |
| Output $ / 1M tokens | $0.13 | $2.08 |
Context
| Field | openai__gpt-oss-20b | qwen__qwen3.5-122b-a10b |
|---|---|---|
| Max context tokens | 131,072 | 262,144 |
| Max output tokens | 117,964 | 65,536 |
Modalities
| Field | openai__gpt-oss-20b | qwen__qwen3.5-122b-a10b |
|---|---|---|
| Input | text | text, image, video |
| Output | text | text |