Compare models
Up to four models side by side. The best value in each row is highlighted. Task scores are heuristics, not benchmark results.
Add at least one more model to compare.
| Attribute | |
|---|---|
| Overview | |
| Company | Inference Net |
| Version | 2 |
| Tier | fast |
| Released | 2026-09-12 |
| Open weights | Yes |
| Parameters | — |
| Status | Active |
| Pricing (USD per 1M tokens) | |
| Input | $0.030 |
| Output | $0.15 |
| Cached input | $0.030 |
| Batch input | — |
| Batch output | — |
| Blended (3 in : 1 out) | $0.060 |
| Est. cost per token | $0.00000006 |
| Capacity | |
| Context window | 128K |
| Max output | 8K |
| Inputs | text |
| Features | |
| Caching | Yes |
| JSON schema | Yes |
| Task fit (heuristic, 1–5) | |
| coding | 3 / 5 |
| reasoning | 2 / 5 |
| math | 2 / 5 |
| summarization | 4 / 5 |
| extraction | 4 / 5 |
| classification | 4 / 5 |
| chat | 3 / 5 |
| creative | 3 / 5 |
| translation | 4 / 5 |
| vision | 1 / 5 |
| long context | 3 / 5 |
| agentic | 1 / 5 |
Prices are USD per 1M tokens from vendor price lists. “—” means the vendor does not publish it.