Pricing · per 1M tokens
Input
$0.140
per million tokens
Output
$0.280
per million tokens
| Cached input | $0.003/Mtok (2% of input — prompt caching) |
|---|---|
| Blended avg cost* | $0.210/Mtok |
Overview
Extremely cheap with aggressive caching. $0.14 in / $0.28 out per 1M; cache hit only $0.0028. 1M context. Aliased as deepseek-chat (non-thinking) and deepseek-reasoner (thinking).
Specifications
| Provider | DeepSeek |
|---|---|
| Context window | 1M tokens |
| Modality | text |
| Parameters | Proprietary |
| Open source | No — proprietary |
| Released | Dec 1, 2025 |
| Status | Current |
| Last updated | Jun 24, 2026 |
| Tags | fast reasoning caching budget |