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 Mar 2026 |
| Status | Current | Current |
| Open weights | No | No |
| Hosts APIs you can call it on | 1 | 7 |
| Price · USD per million tokens, at the lab's own API where it sells the model | ||
| Priced at | Together AI | OpenAI |
| Input | $1.80 | $0.75 |
| Output | $1.80 | $4.50 |
| Cached input | - | $0.075 |
| Batch input / output | - | $0.375 / $2.25 |
| Cheapest anywhere input / output | $1.80 / $1.80 Together AI | $0.75 / $4.50 Databricks |
| 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 | $675 | $502 |
| RAG over documents 2,000 a day, 8K in, 600 out | $929 | $360 |
| Coding agent 1,000 a day, 40K in, 2K out | $2,268 | $603 |
| Overnight batch 20,000 a day, 4K in, 400 out | $4,752 | $1,440 |
| Limits | ||
| Context window | - | 272K tokens |
| Max output | - | 128K tokens |
| Capabilities | ||
| Takes in | Text | Images, Text, PDFs |
| Produces | Text | Text |
| Effort settings as listed by the source | - | none, xhigh |
| Streaming | ||
| Function calling | ||
| JSON mode | ||
| Structured outputs | ||
| Reasoning | ||
| Tool calling | ||
| Prompt caching | ||
| Batch API | ||
| Built-in web search | ||
| Parallel tool calls | ||
| Tool search | ||