computetrail

All models ·deepseek

DeepSeek: R1 Distill Llama 70B

Provider: deepseek · deepseek/deepseek-r1-distill-llama-70b

Input
$0.8 /1M
Output
$0.8 /1M
Context
8,192 tokens

How DeepSeek: R1 Distill Llama 70B pricing compares

At $0.8 / 1M output tokens, DeepSeek: R1 Distill Llama 70B is the 6th-cheapest of 14 deepseek models we track. It's cheaper than 70% of the 392 paid models on computetrail (117th-cheapest overall). Output costs 1.0× its input price ($0.8 / 1M in). For a typical 3:1 input-to-output workload that works out to about $0.80 / 1M blended. Its 8,192 tokens context window ranks 384th-largest of 392 models with a published limit.

Output price history

$0.800$0.80006-2907-2908-27

Across 60 daily snapshots since 2026-06-29, the output price has held steady at $0.8 / 1M — no change so far.

Similar-priced models

ModelProviderOutput $/1MContext
Meta: Llama 4 Maverickmeta-llama$0.81,048,576
Qwen: Qwen-Plusqwen$0.781,000,000
Z.ai: GLM 4.5 Airz-ai$0.85131,072
Meta: Llama 3.3 70B Instructmeta-llama$0.71131,072
Z.ai: GLM 4.6Vz-ai$0.9131,072
Google: Gemini 3.7 Flash (batch)google$0.93751,048,576

Prices are recorded daily from public provider data via OpenRouter and normalized to USD per 1M tokens. See methodology.