DeepSeek V3.1
DeepSeek · Released Aug 2025
A 671-billion-parameter mixture-of-experts model with 37 billion activated parameters and a 161,000-token context window.
- Strengths
- Handles long-context tasks efficiently with MoE architecture and maintains broad capability across code, reasoning, and general text tasks.
- Best for
- Applications requiring extended context windows and balanced performance without the latest optimizations of V3.2 or newer models.
- Limitations
- Superseded by V3.2 Exp and V3.2 released later in 2025; use the newer versions for improved performance and lower inference costs.
Input / 1M
$0.25
Output / 1M
$0.95
Cached input / 1M
$0.13
Context window
163K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in decreased 0.0% out decreased 0.0%
- 90d
- in increased 19.0% out increased 20.3%
- 1y
- in increased 19.0% out increased 20.3%
- Since launch
- in increased 19.0% out increased 20.3%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 8 Sep 2026 | $0.25 | $0.95 | $0.13 | Imported from OpenRouter | openrouter.ai |
| 4 Sep 2026 | $0.55 | $1.65 | $0.55 | Imported from OpenRouter | openrouter.ai |
| 2 Sep 2026 | $0.25 | $0.95 | $0.13 | Imported from OpenRouter | openrouter.ai |
| 22 Aug 2026 | $0.55 | $1.65 | $0.55 | Imported from OpenRouter | openrouter.ai |
| 13 Jul 2026 | $0.25 | $0.95 | $0.13 | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.21 | $0.79 | $0.13 | Imported from OpenRouter | openrouter.ai |