gpt-oss-20b is 10.4× cheaper per million tokens (blended). Hy4 has the larger context window (1,048,576 vs 131,072 tokens, 8.0×).
gpt-oss-20b vs Hy4
Live catalog fields. Best-in-row is highlighted.
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Hy4open
Tencent · tencent__hy4
Identity
| Field | openai__gpt-oss-20b | tencent__hy4 |
|---|---|---|
| Provider | OpenAI | Tencent |
| Slug | openai__gpt-oss-20b | tencent__hy4 |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | openai/gpt-oss-20b | tencent/Hy4 |
Quality
| Field | openai__gpt-oss-20b | tencent__hy4 |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-20b | tencent__hy4 |
|---|---|---|
| Input $ / 1M tokens | $0.03 | $0.42 |
| Cached input $ / 1M | $0.03 | $0.02 |
| Output $ / 1M tokens | $0.13 | $1.25 |
Context
| Field | openai__gpt-oss-20b | tencent__hy4 |
|---|---|---|
| Max context tokens | 131,072 | 1,048,576 |
| Max output tokens | 117,964 | 65,536 |
Modalities
| Field | openai__gpt-oss-20b | tencent__hy4 |
|---|---|---|
| Input | text | text, image |
| Output | text | text |