Skip to main content
Vincony
GR
Groq
Reasoning

DeepSeek R1 Distill (Groq)

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

2 credits / request
Compare with…Added 2026

DeepSeek R1's reasoning capabilities distilled into a Llama 70B architecture, running on Groq's ultra-fast LPU hardware. This model combines DeepSeek's chain-of-thought reasoning with Groq's speed advantage.

Key Features

Chain-of-thought reasoning distilled from DeepSeek R1

Ultra-fast inference on Groq hardware

Strong analytical and math capabilities

70B parameter base for broad knowledge

Ideal Use Cases

1.

Fast reasoning tasks requiring quick analytical responses

2.

Math and logic problems with speed constraints

3.

Real-time tutoring and educational applications

Technical Specifications

Context Window128K tokens
ModalityText → Text
ProviderGroq
CategoryReasoning
Reasoning StyleChain-of-thought (distilled)
LatencyUltra-low (Groq LPU)

API Usage

1curl -X POST https://api.vincony.com/v1/chat/completions \
2 -H "Authorization: Bearer YOUR_API_KEY" \
3 -H "Content-Type: application/json" \
4 -d '{
5 "model": "groq/deepseek-r1-distill-llama-70b",
6 "messages": [
7 { "role": "user", "content": "Hello, DeepSeek R1 Distill (Groq)!" }
8 ]
9 }'

Replace YOUR_API_KEY with your Vincony API key. OpenAI-compatible endpoint — works with any OpenAI SDK.

Compare with Another Model

Or compare up to 3 models

Frequently Asked Questions

Try DeepSeek R1 Distill (Groq) now

Start using DeepSeek R1 Distill (Groq) instantly — 100 free credits, no credit card required. Access 343+ AI models through one platform.

Vincony — Access the World's Best AI Models