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 | - | 22 Sep 2026 |
| Status | Current | Current |
| Open weights | Yes, DeepSeek License (MIT code) | No |
| Hosts APIs you can call it on | 1 | 10 |
| Price · USD per million tokens, at the lab's own API where it sells the model | ||
| Priced at | Fireworks AI | OpenAI |
| Input | $0.21 | $0.10 |
| Output | $0.84 | $0.50 |
| Cached input | $0.0042 | $0.01 |
| Batch input / output | - | $0.05 / $0.25 |
| Long prompts input / output | - | $0.20 / $0.75 above 272K |
| Cheapest anywhere input / output | $0.21 / $0.84 Fireworks AI | $0.10 / $0.50 OpenAI |
| 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 | $107 | $59.40 |
| RAG over documents 2,000 a day, 8K in, 600 out | $81.65 | $44.40 |
| Coding agent 1,000 a day, 40K in, 2K out | $130 | $74.40 |
| Overnight batch 20,000 a day, 4K in, 400 out | $706 | $180 |
| Limits | ||
| Context window | 1M tokens | 922K tokens |
| Max output | 393K tokens | 128K tokens |
| Capabilities | ||
| Takes in | Text, Images | Images, Text, PDFs |
| Produces | Text | Text |
| Effort settings as listed by the source | - | none, xhigh, max |
| Streaming | ||
| Function calling | ||
| JSON mode | ||
| Structured outputs | ||
| Reasoning | ||
| Tool calling | ||
| Prompt caching | ||
| Batch API | ||
| Built-in web search | ||
| Computer use | ||
| Parallel tool calls | ||
| Tool search | ||