BETA
Open-weights reasoning model with chain-of-thought trained via RL. Comparable to o1 on math benchmarks at a fraction of the price.
R1 Distill Llama 70B is a reasoning AI model from DeepSeek. It costs $0.800 per million input tokens and $0.800 per million output tokens (blended $0.800/M), with a 128K-token context window.
Profile inherited from upstream DeepSeek-R1 ↗ — this is a hosted variant of the same open-weights model.
R1 Distill Llama 70B costs $0.800 per million input tokens and $0.800 per million output tokens, for a blended reference rate of $0.800 per million tokens.
R1 Distill Llama 70B supports up to 128K tokens of context (128,000 tokens).
R1 Distill Llama 70B is well suited to Open-weights reasoning, Visible chain-of-thought and Math & code.
R1 Distill Llama 70B is developed and served by DeepSeek.
