Pricing · per 1M tokens
Input
$0.435
per million tokens
Output
$0.870
per million tokens
| Cached input | $0.004/Mtok (1% of input — prompt caching) |
|---|---|
| Blended avg cost* | $0.652/Mtok |
Overview
Higher-capability DeepSeek model with thinking. $0.435 in / $0.87 out per 1M; cache hit $0.003625. 1M context.
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 | reasoning caching mid-tier |