Context Window
131,072
Input tokens
Full-context input ≈ $0.09
Model Cost Profile
Developer: deepseek· Tokenizer: Llama3 · Instruct: deepseek-r1 · Quantization: fp8
Canonical ID: deepseek/deepseek-r1-distill-llama-70b
Pricing updated Apr 24, 2026
Live Pricing
Input: $0.7000
Output: $0.8000
Last synced Apr 24, 2026 · MMLU score via public benchmark data
DeepSeek's R1 Distill Llama 70B model offers an extensive context window of 131,072 tokens, making it ideal for applications requiring in-depth analysis, such as legal document review or comprehensive research tasks. With an input price of $0.70 per million tokens and an output price of $0.80 per million tokens, teams can effectively manage costs while leveraging the model's capabilities for large-scale data processing. This model is particularly beneficial for organizations that need to handle complex queries and generate detailed responses in real-time.
Context Window
131,072
Input tokens
Full-context input ≈ $0.09
Max Output
16,384
Completion tokens
Input Price / 1M
$0.7000
Prompt tokens
Output Price / 1M
$0.8000
Completion tokens
Top Benchmark
79.5
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for DeepSeek: R1 Distill Llama 70B. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.7000
Current Output / 1M
$0.8000
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.7000 |
| Output (Completion) | $0.8000 |
Estimate monthly spend for DeepSeek: R1 Distill Llama 70B based on your workload.
Estimated Monthly Cost
$27
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.