gpt-oss-120b is 10.6× cheaper per million tokens (blended). Qwen3.5-35B-A3B has the larger context window (262,144 vs 131,072 tokens, 2.0×).
gpt-oss-120b vs Qwen3.5-35B-A3B
Live catalog fields. Best-in-row is highlighted.
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Qwen3.5-35B-A3Bopen
Qwen · qwen__qwen3.5-35b-a3b
Identity
| Field | openai__gpt-oss-120b | qwen__qwen3.5-35b-a3b |
|---|---|---|
| Provider | OpenAI | Qwen |
| Slug | openai__gpt-oss-120b | qwen__qwen3.5-35b-a3b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | openai/gpt-oss-120b | Qwen/Qwen3.5-35B-A3B |
Quality
| Field | openai__gpt-oss-120b | qwen__qwen3.5-35b-a3b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-120b | qwen__qwen3.5-35b-a3b |
|---|---|---|
| Input $ / 1M tokens | $0.02 | $0.14 |
| Cached input $ / 1M | $0.02 | $0.05 |
| Output $ / 1M tokens | $0.09 | $1.00 |
Context
| Field | openai__gpt-oss-120b | qwen__qwen3.5-35b-a3b |
|---|---|---|
| Max context tokens | 131,072 | 262,144 |
| Max output tokens | 65,536 | 81,920 |
Modalities
| Field | openai__gpt-oss-120b | qwen__qwen3.5-35b-a3b |
|---|---|---|
| Input | text | text, image, video |
| Output | text | text |