R1 Distill Llama 70B
deepseek-r1-distill-llama-70bDeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across... Built by DeepSeek.
Prices updated
Input price
$0.80
per 1M tokens · Standard
Output price
$0.80
per 1M tokens · Standard
Input limit
8K
tokens
Output limit
7K
tokens
Input formats
Output formats
R1 Distill Llama 70B price history
2 price records since 9/25/2026
R1 Distill Llama 70B cost calculator
$20/month
Standard pricing
Overview
What is R1 Distill Llama 70B?
R1 Distill Llama 70B is a text & reasoning model from DeepSeek. DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across... Its 8K context window and $0.80 input price make it a candidate for quality-focused production applications.
Benchmarks
R1 Distill Llama 70B benchmarks & speed
How R1 Distill Llama 70B scores on standardized evaluations, and where it lands among every model we track.
7.9
Intelligence Index
Reasoning
GPQA Diamond
40.2%
Graduate-level scientific reasoning · top 94%
HLE
5.1%
Humanity's Last Exam · top 79%
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
R1 Distill Llama 70B pricing
Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.
Input · Standard
$0.80
Per 1M tokens
Cached input · Standard
Not available
No listed cached-input rate
Capabilities
R1 Distill Llama 70B Tools
Tools available when using R1 Distill Llama 70B through supported provider APIs.
Function calling
Not supported
Structured outputs
Not supported
JSON mode
Not supported
Reasoning
Supported
Built-in web search
Not supported
Log probabilities
Not supported
Deterministic seed
Supported
Parallel tool calls
Not supported
Prompt caching
Not supported
Strengths and limitations
Strengths
- Measured results (AA Intelligence 7.9) position it for demanding production work.
- A 8K 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 8K 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