DeepSeek V3.2
deepseek-v3.2DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism... Built by DeepSeek.
Prices updated
Input price
$0.26
per 1M tokens · Standard
Output price
$0.42
per 1M tokens · Standard
Input limit
164K
tokens
Output limit
66K
tokens
Input formats
Output formats
DeepSeek V3.2 price history
5 price records since 9/25/2026 · 3 changes
DeepSeek V3.2 cost calculator
$7.28/month
Standard pricing
Overview
What is DeepSeek V3.2?
DeepSeek V3.2 is a text & reasoning model from DeepSeek. DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism... Its 164K context window and $0.26 input price make it a candidate for cost-sensitive, high-throughput applications.
Benchmarks
DeepSeek V3.2 benchmarks & speed
How DeepSeek V3.2 scores on standardized evaluations, and where it lands among every model we track.
16.0
Intelligence Index
Reasoning
GPQA Diamond
75.1%
Graduate-level scientific reasoning · top 63%
HLE
11.2%
Humanity's Last Exam · top 64%
Independent scores from Artificial Analysis and DesignArena · updated 10/5/2026. Higher is better; ranks compare against every model we track with that score.
Rates
DeepSeek V3.2 pricing
Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.
Input · Standard
$0.26
Per 1M tokens
Cached input · Standard
$0.14
Per 1M tokens
Capabilities
DeepSeek V3.2 Tools
Tools available when using DeepSeek V3.2 through supported provider APIs.
Function calling
Supported
Structured outputs
Supported
JSON mode
Supported
Reasoning
Supported
Built-in web search
Not supported
Log probabilities
Supported
Deterministic seed
Supported
Parallel tool calls
Not supported
Prompt caching
Supported
Strengths and limitations
Strengths
- Low input cost at $0.26 per million tokens suits high-volume workloads.
- A 164K context window covers most focused application workflows.
- Supports text & reasoning workloads in one model.
Limitations
- Real-world cost still depends on prompt length, response length and provider-specific billing rules.
- The 164K context window is smaller than several long-context alternatives.
- Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.
Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.
Same provider