MetaDeepSeek R1

R1 Distill Llama 70B pricing

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 multiple benchmarks, including: - AIME 2024 pass@1: 70.0 - MATH-500 pass@1: 94.5 - CodeForces Rating: 1633 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to lar. Live index: 10 priced offers. Best input $0.200 per million tokens from DeepInfra. Best output $0.375 per million tokens from Nscale.

131K context·10 providers·verified Apr 7, 2026
Best input$0.200per 1M tokens · DeepInfra
Best output$0.375per 1M tokens · Nscale

Pricing across providers

Every row is a seller of R1 Distill Llama 70B with token pricing we track. The cheapest input in this snapshot is from DeepInfra. The bar chart shows the same input and output dollars per million for a quick scan.

O
Openrouter
Input / 1M
$0.700
Output / 1M
$0.800
VA
Vercel Ai Gateway
Input / 1M
$0.750
Output / 1M
$0.990
N
Novita
Input / 1M
$0.800
Output / 1M
$0.800
G
Gradient
Input / 1M
$0.990
Output / 1M
$0.990
N
Nscale
Input / 1M
$0.375
Output / 1M
$0.375
N
Nebius
Input / 1M
$0.250
Output / 1M
$0.750
O
Ovhcloud
Input / 1M
$0.670
Output / 1M
$0.670
S
Sambanova
Input / 1M
$0.700
Output / 1M
$1.40
FA
Fireworks AI
Input / 1M
$0.900
Output / 1M
$0.900
D
DeepInfra
Input / 1M
$0.200
Output / 1M
$0.600

Input vs output · per provider

Cost calculator

The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how R1 Distill Llama 70B cost scales with traffic.

Provider

In: $0.700/M·Out: $0.800/M

0.070000¢ / req

0.040000¢ / req

Daily
$11
Monthly
$330
Annual
$4.0K

Model specifications

Context length, caps, and capability flags for R1 Distill Llama 70B. Family: DeepSeek R1. Values follow the main provider (Meta) record in our index.

Context window
131,072 tokens
Max output
131,072 tokens
Vision (images)
No
Tool / function calling
No
Streaming
No
Released
Jan 2025
Primary provider
Meta
Model family
DeepSeek R1

Compare R1 Distill Llama 70B

Jump into a comparison when you want one table for two models instead of two tabs. 6 curated matches for R1 Distill Llama 70B.

Frequently asked questions

Answers pull from the same numbers you see on this page. The short model note from our index: 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 advance...

Yes. R1 Distill Llama 70B is available on Openrouter, Vercel Ai Gateway, Novita, Gradient, Nscale, Nebius, Ovhcloud, Sambanova, Fireworks AI, DeepInfra.

Also from Meta

Other models by Meta with live pricing in our catalog.