Context Window
163,840
Input tokens
Full-context input ≈ $0.07
Model Cost Profile
Developer: deepseek· Tokenizer: DeepSeek · Quantization: fp8
Canonical ID: deepseek/deepseek-v3.2-speciale-20251201
Pricing updated Apr 23, 2026
Live Pricing
Input: $0.4000
Output: $1.20
Last synced Apr 23, 2026 · MMLU score via public benchmark data
DeepSeek V3.2 Speciale, developed by deepseek, offers an extensive context window of 163,840 tokens, making it ideal for applications requiring comprehensive data analysis and long-form content generation. With an input price of $0.40 per million tokens and an output price of $1.20 per million tokens, teams can manage costs effectively while leveraging its capabilities for tasks such as document summarization and complex query handling. This model is particularly beneficial for organizations dealing with large datasets or needing to maintain context over extended interactions, ensuring efficient processing and output generation.
Context Window
163,840
Input tokens
Full-context input ≈ $0.07
Max Output
163,840
Completion tokens
Input Price / 1M
$0.4000
Prompt tokens
Output Price / 1M
$1.20
Completion tokens
Top Benchmark
87.1
GPQA score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for DeepSeek: DeepSeek V3.2 Speciale. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.4000
Current Output / 1M
$1.20
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.4000 |
| Output (Completion) | $1.20 |
| Cache Read | $0.2000 |
Estimate monthly spend for DeepSeek: DeepSeek V3.2 Speciale based on your workload.
Estimated Monthly Cost
$24
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.