R1 Distill Llama 70B

DeepSeek · deepseek/deepseek-r1-distill-llama-70b

← Back to leaderboard

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...

R1 Distill Llama 70B ranks #183 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.80 blended per million tokens, it is cheaper than 57% of models with published API pricing. Its 8,192-token context window is 32.0× smaller than the catalog median (262,144 tokens).

open weightstexttext->text

Context

Max context: 8192
Max output: 7372

Pricing

Input / 1M: 0.80
Output / 1M: 0.80
Blend / 1M: 0.80

Quality

Quality index:

Provider

Provider: DeepSeek
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $0.80per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / monthEst. cost (USD)
1,000,000$0.80
10,000,000$8.00
100,000,000$80.00

Related models

Same lab, similar price, or similar quality — useful next comparisons.

More from DeepSeek

Closest API price