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

DeepSeek: R1 Distill Llama 70B accepts up to 8,192 tokens (8K) of context per request.

How much does DeepSeek: R1 Distill Llama 70B cost per million tokens?

Through Wide Area Intelligence, DeepSeek: R1 Distill Llama 70B costs $0.88 per 1M input tokens and $0.88 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $1.76.

Can I run DeepSeek: R1 Distill Llama 70B on my own hardware?

Yes — DeepSeek: R1 Distill Llama 70B is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 43.3 GB of GPU memory with an 8,192-token context — it fits a single 48 GB card. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

← model directory

deepseek

DeepSeek: R1 Distill Llama 70B

Name: DeepSeek: R1 Distill Llama 70B
Brand: deepseek
Price: 0.8800 USD

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

↓ runs free on your own hardware

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...

specs & pricing

Type: text
Provider: deepseek
Model ID: deepseek/deepseek-r1-distill-llama-70b
Capabilities: reasoning
Context window: 8K tokens
Self-hostable: Yes — runs on your own GPU
Input price: $0.88 / 1M tokens
Output price: $0.88 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.

What it costs to run

cloud · 1M in + 1M out

$1.76

$0.88 for a million input tokens plus $0.88 for a million output tokens, billed from credits only when a request fails over to the cloud.

your hardware

$0 / token

Served from a workstation or on-prem server you own, there is no per-token fee — the marginal cost is power.

AI cost calculator →GPU power cost →

Run it on your own hardware

Estimated GPU memory for DeepSeek: R1 Distill Llama 70B (71B parameters), including the KV cache for a 8,192-token context.

Q4_K_M: ~43.3 GBfits a 48 GB card
Q8_0: ~72.9 GBfits a 80 GB card
FP16 / BF16: ~134.7 GBmulti-GPU or large unified memory

Install the agent on the machine and it dials out to the gateway over a single WebSocket — no port forwarding or inbound firewall rules. Requests for this model go to your node first and fail over to the cloud only when it can't serve.

VRAM calculator →Which GPU do I need? →

/// initialize

Call DeepSeek: R1 Distill Llama 70B through one OpenAI-compatible endpoint.

Serve it from hardware you own, with cloud failover when your nodes are busy or offline.

Run it on your own hardware Try it in chat

no credit card · 2 nodes free · openai-compatible

Frequently asked questions

What is the context window of DeepSeek: R1 Distill Llama 70B?: DeepSeek: R1 Distill Llama 70B accepts up to 8,192 tokens (8K) of context per request.
How much does DeepSeek: R1 Distill Llama 70B cost per million tokens?: Through Wide Area Intelligence, DeepSeek: R1 Distill Llama 70B costs $0.88 per 1M input tokens and $0.88 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $1.76.
Can I run DeepSeek: R1 Distill Llama 70B on my own hardware?: Yes — DeepSeek: R1 Distill Llama 70B is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 43.3 GB of GPU memory with an 8,192-token context — it fits a single 48 GB card. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

More from deepseek

← browse all models