gpt-oss-120b is 3.4× cheaper per million tokens (blended). gpt-oss-120b has the larger context window (131,072 vs 8,192 tokens, 16.0×).
gpt-oss-120b vs Hy-MT2-30B-A3B
Live catalog fields. Best-in-row is highlighted.
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Hy-MT2-30B-A3Bopen
Tencent · tencent__hy-mt2-30b-a3b
Identity
| Field | openai__gpt-oss-120b | tencent__hy-mt2-30b-a3b |
|---|---|---|
| Provider | OpenAI | Tencent |
| Slug | openai__gpt-oss-120b | tencent__hy-mt2-30b-a3b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | openai/gpt-oss-120b | tencent/Hy-MT2-30B-A3B |
Quality
| Field | openai__gpt-oss-120b | tencent__hy-mt2-30b-a3b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-120b | tencent__hy-mt2-30b-a3b |
|---|---|---|
| Input $ / 1M tokens | $0.02 | $0.07 |
| Cached input $ / 1M | $0.02 | — |
| Output $ / 1M tokens | $0.09 | $0.29 |
Context
| Field | openai__gpt-oss-120b | tencent__hy-mt2-30b-a3b |
|---|---|---|
| Max context tokens | 131,072 | 8,192 |
| Max output tokens | 65,536 | 4,096 |
Modalities
| Field | openai__gpt-oss-120b | tencent__hy-mt2-30b-a3b |
|---|---|---|
| Input | text | text |
| Output | text | text |