Context Window
163,840
Input tokens
Full-context input ≈ $0.03
Model Cost Profile
Developer: deepseek· Tokenizer: DeepSeek · Instruct: deepseek-v3.1 · Quantization: fp4
Canonical ID: deepseek/deepseek-v3.1-terminus
Pricing updated Apr 22, 2026
Live Pricing
Input: $0.2100
Output: $0.7900
Last synced Apr 22, 2026 · MMLU score via public benchmark data
DeepSeek V3.1 Terminus offers a substantial context window of 163,840 tokens, making it ideal for complex tasks such as long-form content generation, comprehensive data analysis, and intricate conversational AI applications. With an input price of $0.21 per million tokens and an output price of $0.79 per million tokens, teams can effectively manage costs while leveraging the model for extensive projects that require detailed contextual understanding. This pricing structure allows organizations to scale their usage according to specific project needs, optimizing budget allocation for high-volume tasks.
Context Window
163,840
Input tokens
Full-context input ≈ $0.03
Max Output
—
Not specified
Input Price / 1M
$0.2100
Prompt tokens
Output Price / 1M
$0.7900
Completion tokens
Top Benchmark
83.6
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for DeepSeek: DeepSeek V3.1 Terminus. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.2100
Current Output / 1M
$0.7900
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.2100 |
| Output (Completion) | $0.7900 |
| Cache Read | $0.1300 |
Estimate monthly spend for DeepSeek: DeepSeek V3.1 Terminus based on your workload.
Estimated Monthly Cost
$15
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.