T
Thinking Machines Inkling 2 Mini API providers
As of November 22, 2026, Io Net has the highest reported output speed for Thinking Machines Inkling 2 Mini, 87 tokens per second, and PrimeIntellect has the lowest listed output price, $0.30 per million tokens. 2 providers serve Thinking Machines Inkling 2 Mini on OpenRouter.
- Fastest output 87 tok/s I Io Net
Top 5: PrimeIntellect 62 tok/s
- Lowest latency 1.3 s P PrimeIntellect
Top 5: Io Net 1.6 s
- Lowest price $0.30 / 1M output P PrimeIntellect
Top 5: Io Net $0.35
Output speed by provider
- Io Net 87 tok/s
- PrimeIntellect 62 tok/s
Median output tokens per second reported by OpenRouter, November 22, 2026.
Every provider serving Thinking Machines Inkling 2 Mini
| Provider | Output speed | Time to first token | Input price | Output price | Quantization | Context |
|---|---|---|---|---|---|---|
| Io NetFastest measured provider | 87 tok/s | 1.6 s | $0.08 / 1M | $0.35 / 1M | nvfp4 | 262K |
| PrimeIntellect | 62 tok/s | 1.3 s | $0.075 / 1M | $0.30 / 1M | fp4 | 1.05M |
Provider performance and prices are a snapshot from November 22, 2026. Availability and routing can change.