gpt-oss-20b is 10.3× cheaper per million tokens (blended). Inkling Small has the larger context window (524,288 vs 131,072 tokens, 4.0×).
gpt-oss-20b vs Inkling Small
Live catalog fields. Best-in-row is highlighted.
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Inkling Smallopen
Thinkingmachines · thinkingmachines__inkling-small
Identity
| Field | openai__gpt-oss-20b | thinkingmachines__inkling-small |
|---|---|---|
| Provider | OpenAI | Thinkingmachines |
| Slug | openai__gpt-oss-20b | thinkingmachines__inkling-small |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | openai/gpt-oss-20b | thinkingmachines/Inkling-Small |
Quality
| Field | openai__gpt-oss-20b | thinkingmachines__inkling-small |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-20b | thinkingmachines__inkling-small |
|---|---|---|
| Input $ / 1M tokens | $0.03 | $0.45 |
| Cached input $ / 1M | $0.03 | $0.10 |
| Output $ / 1M tokens | $0.13 | $1.20 |
Context
| Field | openai__gpt-oss-20b | thinkingmachines__inkling-small |
|---|---|---|
| Max context tokens | 131,072 | 524,288 |
| Max output tokens | 117,964 | 262,144 |
Modalities
| Field | openai__gpt-oss-20b | thinkingmachines__inkling-small |
|---|---|---|
| Input | text | text, image, audio |
| Output | text | text |