Thinking Machines: Inkling Small (free) vs Sao10K: Llama 3 8B Lunaris
Thinking Machines: Inkling Small (free) is cheaper on output tokens, while Thinking Machines: Inkling Small (free) offers a larger context window. Choose Thinking Machines: Inkling Small (free) or Sao10K: Llama 3 8B Lunaris based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Thinking Machines: Inkling Small (free) | Sao10K: Llama 3 8B Lunaris |
|---|---|---|
| Provider | Kilo Gateway | Kilo Gateway |
| Input / 1M tokens | $0.00 | $0.04 |
| Output / 1M tokens | $0.00 | $0.05 |
| Context window | 1M | 8K |
| Parameters | — | — |
| Open weights | Yes | No |
| Released | Jul 2026 | Aug 2024 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.