gpt-oss-120b is 46.8× cheaper per million tokens (blended). Inkling has the larger context window (524,288 vs 131,072 tokens, 4.0×).
gpt-oss-120b vs Inkling
Live catalog fields. Best-in-row is highlighted.
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Inklingopen
Thinkingmachines · thinkingmachines__inkling
Identity
| Field | openai__gpt-oss-120b | thinkingmachines__inkling |
|---|---|---|
| Provider | OpenAI | Thinkingmachines |
| Slug | openai__gpt-oss-120b | thinkingmachines__inkling |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | openai/gpt-oss-120b | thinkingmachines/Inkling |
Quality
| Field | openai__gpt-oss-120b | thinkingmachines__inkling |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-120b | thinkingmachines__inkling |
|---|---|---|
| Input $ / 1M tokens | $0.02 | $1.00 |
| Cached input $ / 1M | $0.02 | $0.17 |
| Output $ / 1M tokens | $0.09 | $4.05 |
Context
| Field | openai__gpt-oss-120b | thinkingmachines__inkling |
|---|---|---|
| Max context tokens | 131,072 | 524,288 |
| Max output tokens | 65,536 | 471,859 |
Modalities
| Field | openai__gpt-oss-120b | thinkingmachines__inkling |
|---|---|---|
| Input | text | text, image, audio |
| Output | text | text |