Context Window
131,072
Input tokens
Full-context input ≈ $0.03
Model Cost Profile
Developer: deepseek· Tokenizer: DeepSeek · Quantization: fp8
Canonical ID: deepseek/deepseek-v3.2-20251201
Pricing updated Apr 24, 2026
Live Pricing
Input: $0.2520
Output: $0.3780
Last synced Apr 24, 2026 · MMLU score via public benchmark data
DeepSeek V3.2, developed by deepseek, offers an extensive context window of 163,840 tokens, making it ideal for applications requiring in-depth analysis of large datasets or lengthy documents. Teams leveraging this API model can expect an input cost of $0.26 per million tokens and an output cost of $0.38 per million tokens, allowing for scalable budgeting based on usage. Practical use cases include advanced natural language processing tasks, comprehensive content generation, and complex data extraction, providing organizations with a powerful tool for enhancing their AI capabilities.
Context Window
131,072
Input tokens
Full-context input ≈ $0.03
Max Output
65,536
Completion tokens
Input Price / 1M
$0.2520
Prompt tokens
Output Price / 1M
$0.3780
Completion tokens
Top Benchmark
86.2
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for DeepSeek: DeepSeek V3.2. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.2520
Current Output / 1M
$0.3780
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.2520 |
| Output (Completion) | $0.3780 |
| Cache Read | $0.0252 |
Estimate monthly spend for DeepSeek: DeepSeek V3.2 based on your workload.
Estimated Monthly Cost
$11
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.