Compare models
Up to 4 models side by side: list prices, what a month of real traffic costs, limits and capabilities. The best value in each row is marked with a check.
| Model | |
|---|---|
| Overview | |
| Released | - |
| Status | Older |
| Open weights | Yes, NVIDIA Open Model License |
| Hosts APIs you can call it on | 1 |
| Price · USD per million tokens, at the lab's own API where it sells the model | |
| Priced at | Baseten |
| Input | $0.30 |
| Output | $0.75 |
| Cached input | - |
| Batch input / output | - |
| Cheapest anywhere input / output | $0.30 / $0.75 Baseten |
| Monthly bill · at the price above, 30 days, with each workload's cache and batch use | |
| Chat assistant 5,000 a day, 2K in, 500 out | $146 |
| RAG over documents 2,000 a day, 8K in, 600 out | $171 |
| Coding agent 1,000 a day, 40K in, 2K out | $405 |
| Overnight batch 20,000 a day, 4K in, 400 out | $900 |
| Limits | |
| Context window | - |
| Max output | - |
| Capabilities | |
| Takes in | Text |
| Produces | Text |
| Effort settings as listed by the source | - |
| Streaming | |