gpt-oss-120b is 15.3× cheaper per million tokens (blended). gpt-oss-120b has the larger context window (131,072 vs 32,768 tokens, 4.0×). gpt-oss-120b is open-weights; the other is not.
gpt-oss-120b vs Perceptron Mk1
Live catalog fields. Best-in-row is highlighted.
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Perceptron Mk1
Perceptron · perceptron__perceptron-mk1
Identity
| Field | openai__gpt-oss-120b | perceptron__perceptron-mk1 |
|---|---|---|
| Provider | OpenAI | Perceptron |
| Slug | openai__gpt-oss-120b | perceptron__perceptron-mk1 |
| Status | live | live |
| Open weights | Yes | No |
| License | — | — |
| HuggingFace | openai/gpt-oss-120b | — |
Quality
| Field | openai__gpt-oss-120b | perceptron__perceptron-mk1 |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-120b | perceptron__perceptron-mk1 |
|---|---|---|
| Input $ / 1M tokens | $0.02 | $0.15 |
| Cached input $ / 1M | $0.02 | — |
| Output $ / 1M tokens | $0.09 | $1.50 |
Context
| Field | openai__gpt-oss-120b | perceptron__perceptron-mk1 |
|---|---|---|
| Max context tokens | 131,072 | 32,768 |
| Max output tokens | 65,536 | 8,192 |
Modalities
| Field | openai__gpt-oss-120b | perceptron__perceptron-mk1 |
|---|---|---|
| Input | text | text, image, video |
| Output | text | text |