DeepSeek

DR1 Distill Llama 70BOPEN

R1 Distill Llama 70B (DeepSeek): live API pricing, context window and the best open-source alternatives, tracked daily by OpenSourceAI.tech.

Context window
8K
tokens
Input price
$0.8
per M tokens
Output price
$0.8
per M tokens
Provider
DeepSeek

Prices update automatically — checked hourly against provider list prices.

See model comparisons → Compare all model prices

Benchmarks & performance

Independent benchmark scores for R1 Distill Llama 70B, measured by Artificial Analysis. Higher is better.

2.1×
More intelligence per dollar than Claude Opus 5.
For the same budget, R1 Distill Llama 70B delivers 2.1 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Intelligence index9.9
Math index53.7
GPQA40.2%
MMLU-Pro79.5%
Humanity's Last Exam6.1%
Long Context Reasoning11%
LiveCodeBench26.6%
SciCode31.3%
MATH-50093.5%
AIME67%
AIME 202553.7%
IFBench27.6%
τ²-Bench21.9%
Terminal-Bench Hard1.5%
💰 Blended price$0.787 / 1M tokens
📈 Value12.6 intelligence points per $
Benchmark data by Artificial Analysis

About this model

R1 Distill Llama 70B is an open-weight AI model by DeepSeek. You can download and self-host it for free; the prices below are hosted-API list prices, tracked hourly, for when you prefer convenience over self-hosting.

Frequently asked questions

What is R1 Distill Llama 70B?

R1 Distill Llama 70B is an AI language model from DeepSeek. It is open-weight: you can download it and run it on your own hardware, for free. It scores 9.9 on the Artificial Analysis intelligence index.

Is R1 Distill Llama 70B free?

The weights are free and open — you can self-host R1 Distill Llama 70B and pay nothing per token. If you prefer a hosted API, list prices are $0.8 per million input tokens and $0.8 per million output tokens.

What is R1 Distill Llama 70B good at?

Independent benchmarks from Artificial Analysis give it GPQA 40.2%, MMLU-Pro 79.5%, Humanity's Last Exam 6.1%, Long Context Reasoning 11%, LiveCodeBench 26.6%, SciCode 31.3%, MATH-500 93.5%, AIME 67%, AIME 2025 53.7%, IFBench 27.6%, τ²-Bench 21.9%, Terminal-Bench Hard 1.5%. It is particularly used for mathematical reasoning.

Can I self-host R1 Distill Llama 70B?

Yes. R1 Distill Llama 70B has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.

Open-source alternatives

Depending on your workload, an open-weight model that you can self-host may cut costs dramatically or remove per-token pricing entirely. Our comparison pages put this model side by side with the strongest open-source contenders.

DeepSeek V4 FlashDeepSeekDeepSeek V4 ProDeepSeekDeepSeek V3.2DeepSeekDeepSeek V3.1 TerminusDeepSeekDeepSeek V3.1DeepSeekDeepSeek V3 0324DeepSeek