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 | 17 Apr 2024 | 26 Feb 2024 |
| Status | Current | Current |
| Open weights | Yes, Apache-2.0 | No |
| Hosts APIs you can call it on | 2 | 8 |
| Price · USD per million tokens, at the lab's own API where it sells the model | ||
| Priced at | Fireworks AI | Mistral AI |
| Input | $1.20 | $0.70 |
| Output | $1.20 | $2.10 |
| Cached input | - | $0.07 |
| Batch input / output | - | - |
| Cheapest anywhere input / output | $1.20 / $1.20 Fireworks AI | $0.70 / $2.10 Mistral AI |
| 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 | $450 | $311 |
| RAG over documents 2,000 a day, 8K in, 600 out | $619 | $260 |
| Coding agent 1,000 a day, 40K in, 2K out | $1,512 | $437 |
| Overnight batch 20,000 a day, 4K in, 400 out | $3,168 | $2,184 |
| Limits | ||
| Context window | 66K tokens | 1M tokens |
| Max output | 66K tokens | 1M tokens |
| Capabilities | ||
| Takes in | Text | Text, Images |
| Produces | Text | Text |
| Effort settings as listed by the source | - | low, medium, high |
| Streaming | ||
| Function calling | ||
| JSON mode | ||
| Structured outputs | ||
| Reasoning | ||
| Tool calling | ||
| Prompt caching | ||
| Assistant prefill | ||