gpt-oss-120b is 92.6× cheaper per million tokens (blended). Pareto 26.9 has the larger context window (262,144 vs 131,072 tokens, 2.0×). gpt-oss-120b is open-weights; the other is not.
gpt-oss-120b vs Pareto 26.9
Live catalog fields. Best-in-row is highlighted.
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Pareto 26.9
Unbiased · unbiased__pareto-26.9
Identity
| Field | openai__gpt-oss-120b | unbiased__pareto-26.9 |
|---|---|---|
| Provider | OpenAI | Unbiased |
| Slug | openai__gpt-oss-120b | unbiased__pareto-26.9 |
| Status | live | live |
| Open weights | Yes | No |
| License | — | — |
| HuggingFace | openai/gpt-oss-120b | — |
Quality
| Field | openai__gpt-oss-120b | unbiased__pareto-26.9 |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-120b | unbiased__pareto-26.9 |
|---|---|---|
| Input $ / 1M tokens | $0.02 | $2.50 |
| Cached input $ / 1M | $0.02 | $0.25 |
| Output $ / 1M tokens | $0.09 | $7.50 |
Context
| Field | openai__gpt-oss-120b | unbiased__pareto-26.9 |
|---|---|---|
| Max context tokens | 131,072 | 262,144 |
| Max output tokens | 65,536 | 131,072 |
Modalities
| Field | openai__gpt-oss-120b | unbiased__pareto-26.9 |
|---|---|---|
| Input | text | text, image |
| Output | text | text |