gpt-oss-120b is 44.9× cheaper per million tokens (blended).
gpt-oss-120b vs Qwen3 VL 235B A22B Instruct
Live catalog fields. Best-in-row is highlighted.
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Qwen3 VL 235B A22B Instructopen
Qwen · qwen__qwen3-vl-235b-a22b-instruct
Identity
| Field | openai__gpt-oss-120b | qwen__qwen3-vl-235b-a22b-instruct |
|---|---|---|
| Provider | OpenAI | Qwen |
| Slug | openai__gpt-oss-120b | qwen__qwen3-vl-235b-a22b-instruct |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | openai/gpt-oss-120b | Qwen/Qwen3-VL-235B-A22B-Instruct |
Quality
| Field | openai__gpt-oss-120b | qwen__qwen3-vl-235b-a22b-instruct |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-120b | qwen__qwen3-vl-235b-a22b-instruct |
|---|---|---|
| Input $ / 1M tokens | $0.01 | $0.21 |
| Cached input $ / 1M | $0.01 | $0.10 |
| Output $ / 1M tokens | $0.04 | $1.90 |
Context
| Field | openai__gpt-oss-120b | qwen__qwen3-vl-235b-a22b-instruct |
|---|---|---|
| Max context tokens | 131,072 | 131,072 |
| Max output tokens | 65,536 | 32,768 |
Modalities
| Field | openai__gpt-oss-120b | qwen__qwen3-vl-235b-a22b-instruct |
|---|---|---|
| Input | text | text, image |
| Output | text | text |