DeepSeek R1 Distill Llama 70B
deepseek/deepseek-r1-distill-llama-70b
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...
Code Examples
import requests
response = requests.post(
"https://neurongate.net/v1/chat/completions",
headers={
"Authorization": "Bearer ng-your-api-key",
"Content-Type": "application/json"
},
json={
"model": "deepseek/deepseek-r1-distill-llama-70b",
"messages": [
{"role": "user", "content": "Hello!"}
]
}
)
print(response.json()["choices"][0]["message"]["content"])Pricing Details
| Example | Cost |
|---|---|
| 1K input tokens (short prompt) | $0.00080 |
| 1K in + 500 out (typical response) | $0.00120 |
| 10K in + 2K out (document analysis) | $0.00960 |
| 100K in + 10K out (large context) | $0.0880 |
Prices in USD. Billed per actual token usage. Prepay with USDT, USDC, ETH, or BTC.
Frequently Asked Questions
Capabilities
Context Window
~96K words of text
Modalities
Related Blog Posts
DeepSeek Deprecations Show Why Aliases Matter
A July 2026 news analysis of DeepSeek API model deprecations and the operational value of aliases and migration windows.
DeepSeek R1 Made Reasoning Feel Like Infrastructure
After the January R1 release, teams started treating reasoning models less like demos and more like production infrastructure decisions.
DeepSeek R1 Made Routing a Board-Level Question
A January 2025 news analysis of DeepSeek R1, open reasoning models, and why teams needed provider routing before testing production traffic.