TokenDealHub
中文

DeepSeek: R1 Distill Llama 70Bdeepseek

Bottom Line

DeepSeek: R1 Distill Llama 70B: $0.80/1M input, $0.80/1M output, 8K context, CPS grade B. 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...

API Pricing (per 1M tokens)

Input$0.80
Output$0.80
Cache Read—
Cache Write—
Blended (3:1)$0.80

Specs & Performance

Context Length8K
Max Output7K
Intelligence8
Coding11
Math54
Speed—
TTFT—
CPS GradeB
Input / Output Modalitiestext → text

More from deepseek

DeepSeek: DeepSeek V4.1 Flash 1017
$0.15 / $0.60
DeepSeek: DeepSeek V4 Pro 0423
$0.48 / $0.96
DeepSeek: DeepSeek V4 Flash 0423
$0.09 / $0.18
DeepSeek: DeepSeek V3.2 Speciale
$0.29 / $0.43
DeepSeek: R1 Distill Qwen 32B
$0.29 / $0.29
DeepSeek: DeepSeek V4.1 Flash
$0.02 / $1.00

Looking for cheaper alternatives?

Find the cheapest model by task, or compare two models head-to-head.

Cheapest by task →Compare two models →Compare all models →

FAQ

How much does the DeepSeek: R1 Distill Llama 70B API cost?

DeepSeek: R1 Distill Llama 70B costs $0.80/1M input tokens and $0.80/1M output tokens. Blended cost at a 3:1 ratio is about $0.80/1M tokens.

What is the context window of DeepSeek: R1 Distill Llama 70B?

DeepSeek: R1 Distill Llama 70B supports a 8K token context window with up to 7K output tokens.

Is DeepSeek: R1 Distill Llama 70B worth it?

DeepSeek: R1 Distill Llama 70B has a CPS grade of B (score 60), intelligence index 8, coding index 11. Use the compare page to benchmark against rivals.