DeepSeek
DeepSeek V3.2
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.
At a glance
- Input / 1M
- $0.26
- Output / 1M
- $0.42
- Context
- 164K
- Max output
- 147K
- Intelligence
- 21.5
- Released
- Dec 2025
Pricing
DeepSeek V3.2 API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $0.26 |
|---|---|
| Output tokensPer 1M tokens | $0.42 |
| Cached input (read)Per 1M tokens | $0.14 |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$0.73
per 1,000 requests
Coding task
30K in, 4K out
$9.45
per 1,000 requests
Long document summary
150K in, 2K out
$39.69
per 1,000 requests
Benchmarks
DeepSeek V3.2 benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
21.5
Coding index
44.2
Agentic index
Not available
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 164K tokens
- Max output
- 147K tokens
- Input types
- Text
- Output types
- Text
- Reasoning effort
- Not available
- Release date
- December 1, 2025
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
DeepSeek V3.2 vs other models
See how DeepSeek V3.2 stacks up head to head on price, benchmarks, and features.
VSDeepSeek V3.2 vs DeepSeek V4 Flash 0423
DeepSeek vs DeepSeek
See comparisonVSDeepSeek V3.2 vs Hy3
DeepSeek vs Tencent
See comparisonVSDeepSeek V3.2 vs Solar Mini 4
DeepSeek vs Upstage
See comparisonVSDeepSeek V3.2 vs MiMo-V2.5
DeepSeek vs Xiaomi
See comparisonVSDeepSeek V3.2 vs DeepSeek V4 Pro 0423
DeepSeek vs DeepSeek
See comparisonVS
DeepSeek V3.2 vs Gemma 4 26B A4B
DeepSeek vs Google
See comparisonMore DeepSeek V3.2 comparisons
Alternatives
DeepSeek V3.2 alternatives
Similar models worth considering, and where each one has the edge.
DeepSeek
DeepSeek V4 Pro 0423
Tencent
Hy3
Xiaomi
MiMo-V2.5
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does DeepSeek V3.2 cost?
DeepSeek V3.2 costs $0.26 per 1M input tokens and $0.42 per 1M output tokens through the API. A typical chat message costs about $0.73 per 1,000 messages.
What is the context window of DeepSeek V3.2?
DeepSeek V3.2 accepts up to 164K tokens of input and can write up to 147K tokens in a single response.
What is the best alternative to DeepSeek V3.2?
DeepSeek V4 Pro 0423 from DeepSeek is a strong alternative. It offers: 1.0x cheaper output, higher intelligence score, larger 1.05m context.
Can I use DeepSeek V3.2 alongside other models?
Yes. Shortcut Chat sends one prompt to DeepSeek V3.2 and any other models you pick at the same time, so you can compare answers side by side.
Try DeepSeek V3.2 next to every other model.
Use DeepSeek V3.2 alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.