gpt-oss-20b is 24.7× cheaper per million tokens (blended). gpt-oss-20b has the larger context window (131,072 vs 128,000 tokens).
gpt-oss-20b vs Qwen3 235B A22B Thinking 2507
Live catalog fields. Best-in-row is highlighted.
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Qwen3 235B A22B Thinking 2507open
Qwen · qwen__qwen3-235b-a22b-thinking-2507
Identity
| Field | openai__gpt-oss-20b | qwen__qwen3-235b-a22b-thinking-2507 |
|---|---|---|
| Provider | OpenAI | Qwen |
| Slug | openai__gpt-oss-20b | qwen__qwen3-235b-a22b-thinking-2507 |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | openai/gpt-oss-20b | Qwen/Qwen3-235B-A22B-Thinking-2507 |
Quality
| Field | openai__gpt-oss-20b | qwen__qwen3-235b-a22b-thinking-2507 |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-20b | qwen__qwen3-235b-a22b-thinking-2507 |
|---|---|---|
| Input $ / 1M tokens | $0.03 | $0.45 |
| Cached input $ / 1M | $0.03 | — |
| Output $ / 1M tokens | $0.13 | $3.50 |
Context
| Field | openai__gpt-oss-20b | qwen__qwen3-235b-a22b-thinking-2507 |
|---|---|---|
| Max context tokens | 131,072 | 128,000 |
| Max output tokens | 117,964 | 16,384 |
Modalities
| Field | openai__gpt-oss-20b | qwen__qwen3-235b-a22b-thinking-2507 |
|---|---|---|
| Input | text | text |
| Output | text | text |