token.app › Compare › gpt-oss-120b vs Inkling Small
gpt-oss-120b vs Inkling Small
gpt-oss-120b is 9.1× cheaper per token on a blended 3:1 basis. Inkling Small accepts the larger context window (524K).
Head to head
Blended price uses a 3:1 input:output mix
| gpt-oss-120b | Inkling Small | |
|---|---|---|
| Provider | OpenAI | Thinkingmachines |
| Input $/1M | $0.037 | $0.450 |
| Output $/1M | $0.170 | $1.20 |
| Blended $/1M | $0.070 | $0.637 |
| Context window | 131K | 524K |
| Max output | 131K | 262K |
| Released | Aug 2025 | Jul 2026 |
| Licence | Open weights | Open weights |
Choose gpt-oss-120b if…
- Costs less per token — $0.070 vs $0.637 blended
Choose Inkling Small if…
- Larger context window (524K)
- Newer model (released Jul 2026)
FAQ
Which is better, gpt-oss-120b or Inkling Small?
We do not hold independently-run benchmark scores covering both gpt-oss-120b and Inkling Small, so we make no quality claim. Their pricing and specifications are compared on this page.
Is gpt-oss-120b cheaper than Inkling Small?
gpt-oss-120b is cheaper: $0.070 versus $0.637 per million tokens blended at 3:1 input:output. Input alone: $0.037 vs $0.450. Output alone: $0.170 vs $1.20.
What context windows do gpt-oss-120b and Inkling Small have?
gpt-oss-120b: 131,072 tokens. Inkling Small: 524,288 tokens.
Who makes gpt-oss-120b and Inkling Small?
gpt-oss-120b is made by OpenAI. Inkling Small is made by Thinkingmachines.