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 | 26 Dec 2024 |
| Status | Older |
| Open weights | Yes, DeepSeek License (MIT code) |
| Hosts APIs you can call it on | 2 |
| Price · USD per million tokens, at the lab's own API where it sells the model | |
| Priced at | DeepSeek |
| Input | $0.28 |
| Output | $0.42 |
| Cached input | $0.028 |
| Batch input / output | - |
| Cheapest anywhere input / output | $0.19 / $0.38 Inference APIs |
| 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 | $92.82 |
| RAG over documents 2,000 a day, 8K in, 600 out | $89.04 |
| Coding agent 1,000 a day, 40K in, 2K out | $150 |
| Overnight batch 20,000 a day, 4K in, 400 out | $773 |
| Limits | |
| Context window | 131K tokens |
| Max output | 8K tokens |
| Capabilities | |
| Takes in | Text |
| Produces | Text |
| Effort settings as listed by the source | - |
| Streaming | |
| Function calling | |
| JSON mode | |
| Structured outputs | |
| Tool calling | |
| Prompt caching | |
| Parallel tool calls | |