T
Thinking Machines Inkling 2 Small API providers
As of November 14, 2026, Cloudflare has the highest reported output speed for Thinking Machines Inkling 2 Small, 305 tokens per second, and PrimeIntellect has the lowest listed output price, $0.50 per million tokens. 6 providers serve Thinking Machines Inkling 2 Small on OpenRouter.
- Fastest output 305 tok/s C Cloudflare
Top 5: Together 191 tok/s, DeepInfra 162 tok/s, Nebius 153 tok/s, Modal 150 tok/s
- Lowest latency 0.3 s N Nebius
Top 5: Cloudflare 0.3 s, Together 0.4 s, DeepInfra 0.7 s, Modal 0.8 s
- Lowest price $0.50 / 1M output P PrimeIntellect
Top 5: DeepInfra $0.95, Cloudflare $1.00, Modal $1.00, Nebius $1.00
Output speed by provider
- Cloudflare 305 tok/s
- Together 191 tok/s
- DeepInfra 162 tok/s
- Nebius 153 tok/s
- Modal 150 tok/s
- PrimeIntellect 78 tok/s
Median output tokens per second reported by OpenRouter, November 14, 2026.
Every provider serving Thinking Machines Inkling 2 Small
| Provider | Output speed | Time to first token | Input price | Output price | Quantization | Context |
|---|---|---|---|---|---|---|
| CloudflareFastest measured provider | 305 tok/s | 0.3 s | $0.30 / 1M | $1.00 / 1M | Not published | 1.05M |
| Together | 191 tok/s | 0.4 s | $0.30 / 1M | $1.00 / 1M | Not published | 1.05M |
| DeepInfra | 162 tok/s | 0.7 s | $0.285 / 1M | $0.95 / 1M | fp4 | 262K |
| Nebius | 153 tok/s | 0.3 s | $0.30 / 1M | $1.00 / 1M | fp4 | 1.05M |
| Modal | 150 tok/s | 0.8 s | $0.30 / 1M | $1.00 / 1M | nvfp4 | 1.05M |
| PrimeIntellect | 78 tok/s | 1.1 s | $0.15 / 1M | $0.50 / 1M | fp4 | 1.05M |
Provider performance and prices are a snapshot from November 14, 2026. Availability and routing can change.
