gpt-oss-120b is 12.2× cheaper per million tokens (blended). Ternary Bonsai 2 27B has the larger context window (262,144 vs 131,072 tokens, 2.0×).
gpt-oss-120b vs Ternary Bonsai 2 27B
Live catalog fields. Best-in-row is highlighted.
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Ternary Bonsai 2 27Bopen
Prism Ml · prism-ml__ternary-bonsai-2-27b
Identity
| Field | openai__gpt-oss-120b | prism-ml__ternary-bonsai-2-27b |
|---|---|---|
| Provider | OpenAI | Prism Ml |
| Slug | openai__gpt-oss-120b | prism-ml__ternary-bonsai-2-27b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | openai/gpt-oss-120b | prism-ml/Ternary-Bonsai-2-27B-gguf |
Quality
| Field | openai__gpt-oss-120b | prism-ml__ternary-bonsai-2-27b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-120b | prism-ml__ternary-bonsai-2-27b |
|---|---|---|
| Input $ / 1M tokens | $0.01 | $0.07 |
| Cached input $ / 1M | $0.01 | $0.04 |
| Output $ / 1M tokens | $0.04 | $0.50 |
Context
| Field | openai__gpt-oss-120b | prism-ml__ternary-bonsai-2-27b |
|---|---|---|
| Max context tokens | 131,072 | 262,144 |
| Max output tokens | 65,536 | 32,768 |
Modalities
| Field | openai__gpt-oss-120b | prism-ml__ternary-bonsai-2-27b |
|---|---|---|
| Input | text | text, image |
| Output | text | text |