Qwen3.8 Omni Flash is 1.2× cheaper per million tokens (blended). Qwen3.8 Omni Flash has the larger context window (1,000,000 vs 131,072 tokens, 7.6×). gpt-oss-120b is open-weights; the other is not.
gpt-oss-120b vs Qwen3.8 Omni Flash
Live catalog fields. Best-in-row is highlighted.
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Qwen3.8 Omni Flash
Qwen · qwen__qwen3.8-omni-flash
Identity
| Field | openai__gpt-oss-120b | qwen__qwen3.8-omni-flash |
|---|---|---|
| Provider | OpenAI | Qwen |
| Slug | openai__gpt-oss-120b | qwen__qwen3.8-omni-flash |
| Status | live | live |
| Open weights | Yes | No |
| License | — | — |
| HuggingFace | openai/gpt-oss-120b | — |
Quality
| Field | openai__gpt-oss-120b | qwen__qwen3.8-omni-flash |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-120b | qwen__qwen3.8-omni-flash |
|---|---|---|
| Input $ / 1M tokens | $0.15 | $0.15 |
| Cached input $ / 1M | $0.07 | $0.02 |
| Output $ / 1M tokens | $0.60 | $0.47 |
Context
| Field | openai__gpt-oss-120b | qwen__qwen3.8-omni-flash |
|---|---|---|
| Max context tokens | 131,072 | 1,000,000 |
| Max output tokens | 65,536 | 131,072 |
Modalities
| Field | openai__gpt-oss-120b | qwen__qwen3.8-omni-flash |
|---|---|---|
| Input | text | text, image, audio, video |
| Output | text | text |