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 | - | 2 Sep 2026 |
| Status | Current | Current |
| Open weights | Yes, Llama Community License | No |
| Hosts APIs you can call it on | 1 | 2 |
| Price · USD per million tokens, at the lab's own API where it sells the model | ||
| Priced at | Vercel AI Gateway | Meta Model API |
| Input | $0.72 | $0.10 |
| Output | $0.72 | $0.20 |
| Cached input | - | $0.002 |
| Batch input / output | - | - |
| Cheapest anywhere input / output | $0.72 / $0.72 Vercel AI Gateway | $0.10 / $0.20 Meta Model API |
| 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 | $270 | $36.18 |
| RAG over documents 2,000 a day, 8K in, 600 out | $372 | $31.68 |
| Coding agent 1,000 a day, 40K in, 2K out | $907 | $49.68 |
| Overnight batch 20,000 a day, 4K in, 400 out | $1,901 | $288 |
| Limits | ||
| Context window | 128K tokens | 1M tokens |
| Max output | 8K tokens | 131K tokens |
| Capabilities | ||
| Takes in | Text, Images | Images, Text, Video, PDFs |
| Produces | Text | Text |
| Effort settings as listed by the source | - | minimal, xhigh |
| Streaming | ||
| Function calling | ||
| JSON mode | ||
| Structured outputs | ||
| Reasoning | ||
| Tool calling | ||
| Prompt caching | ||
| Built-in web search | ||
| Parallel tool calls | ||