DeepSeek R1 Distill 70B
DeepSeek · dense · 70.6B parameters · 131,072 context
Parameters
70.6B
Context Window
128K tokens
Architecture
Dense
Best GPU
H200 SXM
Cheapest API
$0.00/M
Quality Score
88/100
Intelligence Brief
DeepSeek R1 Distill 70B is a 70.6B parameter DENSE model from DeepSeek, featuring Grouped Query Attention (GQA) with 80 layers and 8,192 hidden dimensions. With a 131,072 token context window, it supports tools, structured output, code, math, multilingual, reasoning. On standardized benchmarks, it achieves MMLU 90.8, HumanEval 71.7, GSM8K 97.3. The most cost-effective API deployment is via scaleway at $0.00/M output tokens. For self-hosted inference, H200 SXM delivers optimal throughput at $2553/month.
Provider pricing
6 providers · canonical: together| Provider | Input $/M | Output $/M ▲ | Notes |
|---|---|---|---|
| scaleway | free | free | cheapest input · cheapest output |
| featherless | free | free | cheapest input · cheapest output |
| openrouter | $0.700 | $0.800 | — |
| novita | $0.800 | $0.800 | — |
| togethercanonical | $0.880 | $0.880 | — |
| fireworks | $0.900 | $0.900 | — |
Prices update via the nightly pricing cron + admin approvals at /admin/ingest-queue. The leaderboard's Input/Output cells show the canonical rate above; this table shows the full spread.
Recent changes
Loading…
Related models
5 suggestions- DeepSeek R1 Distill 1.5BDeepSeek R1 · 1.5B—
- DeepSeek R1 Distill 14BDeepSeek R1 · 14.8B$0.300/M out
- DeepSeek R1 Distill 32BDeepSeek R1 · 32.8B$0.290/M out
- DeepSeek R1 Distill 8BDeepSeek R1 · 8B$0.200/M out
- DeepSeek R1DeepSeek R1 · 37B$2.00/M out
Picks: same family first, then same vendor within ±2× params, then top tag-overlap matches. Price shown is the cheapest Output $/M across providers — the row's page shows the canonical anchor.
Architecture Details
Memory Requirements
BF16 Weights
141.2 GB
FP8 Weights
70.6 GB
INT4 Weights
35.3 GB
GPU Compatibility Matrix
DeepSeek R1 Distill 70B is compatible with 37% of GPU configurations across 41 GPUs at 3 precision levels.
GPU Recommendations
FP8 · 1 GPU · tensorrt-llm
100/100
score
Throughput
560.0 tok/s
Latency (ITL)
1.8ms
Est. TTFT
0ms
Cost/Month
$2553
Cost/M Tokens
$1.73
FP8 · 1 GPU · tensorrt-llm
100/100
score
Throughput
474.0 tok/s
Latency (ITL)
2.1ms
Est. TTFT
0ms
Cost/Month
$940
Cost/M Tokens
$0.75
FP8 · 1 GPU · tensorrt-llm
100/100
score
Throughput
474.0 tok/s
Latency (ITL)
2.1ms
Est. TTFT
0ms
Cost/Month
$2838
Cost/M Tokens
$2.28
Deployment Options
API Deployment
scaleway
$0.00/M
output tokens
Single GPU
H200 SXM
$2553/mo
Min VRAM: 71 GB
Multi-GPU
H100 SXM x2
560.0 tok/s
TP· $3587/mo
API Pricing Comparison
| Provider | Input $/M | Output $/M | Badges |
|---|---|---|---|
| scaleway | $0.00 | $0.00 | Cheapest |
| featherless | $0.00 | $0.00 | |
| openrouter | $0.70 | $0.80 | |
| novita | $0.80 | $0.80 | |
| together | $0.88 | $0.88 | |
| fireworks | $0.90 | $0.90 |
Cost Analysis
| Provider | Input $/M | Output $/M | ~Monthly Cost |
|---|---|---|---|
| scalewayBest Value | $0.00 | $0.00 | $0 |
| featherless | $0.00 | $0.00 | $0 |
| openrouter | $0.70 | $0.80 | $8 |
| novita | $0.80 | $0.80 | $8 |
| together | $0.88 | $0.88 | $9 |
| fireworks | $0.90 | $0.90 | $9 |
Cost per 1,000 Requests
Short (500 tok)
$0.00
via scaleway
Medium (2K tok)
$0.00
via scaleway
Long (8K tok)
$0.00
via scaleway
Performance Estimates
Throughput by GPU
VRAM Breakdown (H200 SXM, FP8)
Precision Impact
bf16
141.2 GB
weights/GPU
fp8
70.6 GB
weights/GPU
~560.0 tok/s
int4
35.3 GB
weights/GPU
Quality Benchmarks
Capabilities
Features
Supported Frameworks
Supported Precisions
Where to Deploy DeepSeek R1 Distill 70B
Self-Hosted Infrastructure
Similar Models
DeepSeek R1 Distill 32B
32.8B params · dense
Quality: 88
from $0.29/M
Llama 3 70B 1M Context
70.6B params · dense
Quality: 50
from $0.74/M
Llama 3 70B
70.6B params · dense
Quality: 80
from $0.00/M
Llama 3.1 70B
70.6B params · dense
Quality: 75
from $0.00/M
Llama 3.3 70B
70.6B params · dense
Quality: 77
from $0.00/M
Frequently Asked Questions
How much VRAM does DeepSeek R1 Distill 70B need for inference?
DeepSeek R1 Distill 70B requires approximately 141.2 GB of VRAM at BF16 precision, 70.6 GB at FP8, or 35.3 GB at INT4 quantization. Additional VRAM is needed for KV-cache (327680 bytes per token) and activations (~2.50 GB).
What is the best GPU for DeepSeek R1 Distill 70B?
The top recommended GPU for DeepSeek R1 Distill 70B is the H200 SXM using FP8 precision. It achieves approximately 560.0 tokens/sec at an estimated cost of $2553/month ($1.73/M tokens). Score: 100/100.
How much does DeepSeek R1 Distill 70B inference cost?
DeepSeek R1 Distill 70B API inference starts from $0.00/M input tokens and $0.00/M output tokens. Self-hosted inference costs depend on your GPU configuration — use our ROI calculator for a detailed breakdown.