DeepSeek V3.2
DeepSeek · Released Dec 2025
DeepSeek V3.2 is a 671-billion-parameter mixture-of-experts model with 37 billion activated parameters and a 163,840-token context window.
- Strengths
- Balances reasoning capability and inference speed through its mixture-of-experts architecture, activating only a fraction of its total parameters per token.
- Best for
- Tasks requiring both strong reasoning and low latency, such as code generation, math problem-solving, and multi-turn conversations at scale.
- Limitations
- Superseded by V4 Flash and V4 Pro released in April 2026, which offer better performance and efficiency; V3.2 remains available but represents an older generation of DeepSeek's frontier models.
Input / 1M
$0.269
Output / 1M
$0.4
Cached input / 1M
$0.1345
Context window
163K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in decreased 0.0% out decreased 0.0%
- 90d
- in increased 17.6% out increased 16.6%
- 1y
- in increased 17.6% out increased 16.6%
- Since launch
- in increased 17.6% out increased 16.6%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 30 Aug 2026 | $0.269 | $0.4 | $0.1345 | Imported from OpenRouter | openrouter.ai |
| 29 Aug 2026 | $0.269 | $0.4 | $0.1345 | Imported from OpenRouter | openrouter.ai |
| 28 Aug 2026 | $0.269 | $0.4 | $0.1345 | Imported from OpenRouter | openrouter.ai |
| 22 Aug 2026 | $0.26 | $0.38 | $0.13 | Imported from OpenRouter | openrouter.ai |
| 9 Aug 2026 | $0.269 | $0.4 | $0.1345 | Imported from OpenRouter | openrouter.ai |
| 8 Aug 2026 | $0.269 | $0.4 | $0.1345 | Imported from OpenRouter | openrouter.ai |
| 15 Jul 2026 | $0.269 | $0.4 | $0.1345 | Imported from OpenRouter | openrouter.ai |
| 10 Jul 2026 | $0.2145 | $0.3218 | $0.0214 | Imported from OpenRouter | openrouter.ai |
| 27 Jun 2026 | $0.2288 | $0.3432 | $0.0229 | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.2288 | $0.3432 | — | Imported from OpenRouter | openrouter.ai |