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 | - | 5 Dec 2024 |
| Status | Older Newer: Nova 2 Lite | Current |
| Open weights | No | No |
| Hosts APIs you can call it on | 1 | 3 |
| Price · USD per million tokens, at the lab's own API where it sells the model | ||
| Priced at | EmpirioLabs AI | Amazon Nova |
| Input | $0.069 | $0.06 |
| Output | $0.28 | $0.24 |
| Cached input | $0.0386 | - |
| Batch input / output | - | - |
| Cheapest anywhere input / output | $0.069 / $0.28 EmpirioLabs AI | $0.06 / $0.24 Amazon Nova |
| 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 | $38.96 | $36.00 |
| RAG over documents 2,000 a day, 8K in, 600 out | $35.90 | $37.44 |
| Coding agent 1,000 a day, 40K in, 2K out | $74.06 | $86.40 |
| Overnight batch 20,000 a day, 4K in, 400 out | $233 | $202 |
| Limits | ||
| Context window | 317K tokens | 300K tokens |
| Max output | 10K tokens | 10K tokens |
| Capabilities | ||
| Takes in | Text, Images | Text, Images, PDFs |
| Produces | Text | Text |
| Effort settings as listed by the source | - | - |
| Streaming | ||
| Function calling | ||
| JSON mode | ||
| Structured outputs | ||
| Tool calling | ||
| Prompt caching | ||