D
R1 Distill Llama 70BOPEN
DeepSeek R1 Distill Llama 70B is a distilled large language model based on Llama-3.3-70B-Instruct, using outputs from DeepSeek R1.
Prices update automatically — checked daily against provider list prices.
- $0.8 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 22% of the 191 open-weight models tracked here
- 9 of 14 DeepSeek models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for R1 Distill Llama 70B, measured by Artificial Analysis. Higher is better.
Models at this level cost $0.2 per 1M tokens (median of 23) — this one costs $0.8.
Cheaper and better on this index: GLM 5.3 Flash · Gemini 3.7 Flash · Gemini 3.7 Flash (batch) and 89 more
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 daily, 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 9.8 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 5.1%, Long Context Reasoning 9.3%, 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.