DeepSeek logo

DeepSeek R1 Distill Llama 70B

Deprecated
Pricing & Specs API
Free REST API for prices, specs and benchmarks
DeepSeek R1 Distill Llama 70B is DeepSeek's language model with a 131K context window and up to 8K output tokens, available from 8 providers, starting at $0.2 / 1M input and $0.375 / 1M output. A 70B Llama-based model distilled from DeepSeek R1's chain-of-thought reasoning, combining Llama's architecture with R1's advanced reasoning capabilities.
Specifications
Canonical IDdeepseek-r1-distill-llama-70b
TypeLanguage
StatusDeprecated
CreatorDeepSeekDeepSeek
Providers
Context Window131K tokens
Max Output8K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters70B
HuggingFace Likes770
HuggingFace Downloads (30d)171,910
HuggingFace Downloads (all-time)4,433,062
Release Date · 2 years ago
Knowledge Cutoff · 2 years ago
Deprecation Date
Benchmarks
Intelligence Index
#384
Math Index
#160
MMLU-Pro
#137
GPQA
#450
HLE
#379
LiveCodeBench
#246
AIME
#53
IFBench
#379
Time to First Token
#91
SciCode
#309
MATH-500
#58
AIME 2025
#160
LCR
#394
TerminalBench Hard
#343
TAU2
#319
Output TPS
#351

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
DeepInfra logo
DeepInfra
deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
$0.2$0.6
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b
$0.9$0.9
Gradient AI logo
Gradient AI
gradient_ai/deepseek-r1-distill-llama-70b
$0.99$0.99
Novita logo
Novita
novita/deepseek/deepseek-r1-distill-llama-70b
$0.8$0.8
Nscale logo
Nscale
nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
$0.375$0.375
OVHcloud logo
OVHcloud
ovhcloud/DeepSeek-R1-Distill-Llama-70B
$0.67$0.67
Together AI logo
Together AI
together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
$2.00$2.00
Vercel AI Gateway logo
Vercel AI Gateway
vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b
$0.75$0.99

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host DeepSeek R1 Distill Llama 70B, ranked by cheapest on-demand price. The model needs about 168 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NP40sAzure4× AMD Alveo U250 FPGA (64GB)256 GB$6.60/hr
g2-standard-96GCP8× nvidia-l4192 GB$7.98/hr
g7e.12xlargeAWS2× RTX PRO Server 6000192 GB$8.29/hr
7 more instances can run DeepSeek R1 Distill Llama 70B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
DeepSeek R1T2 Chimera164K——Available
DeepSeek R1 528164K$0.200$0.250Deprecated
DeepSeek R1 Distill Qwen 32B131K$0.150$0.150Available
DeepSeek R1 Distill Llama 70B131K$0.200$0.375Current
DeepSeek R1164K$0.280$0.400Deprecated
DeepSeek R1 Distill Qwen 14B—131K$0.070$0.070Deprecated
DeepSeek R1 Distill Llama 8B—131K$0.025$0.025Available
DeepSeek R1 Distill Qwen 1.5B—131K$0.090$0.090Deprecated
DeepSeek R1 528 Turbo—33K$1.00$3.00Available
DeepSeek R1 528B—128K——Deprecated
DeepSeek R1 671B—131K$0.800$0.800Available

Model IDs

accounts/fireworks/models/deepseek-r1-distill-llama-70b
deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
deepseek-llm-r1-distill-llama-70b
deepseek-r1-distill-llama-70b
deepseek/deepseek-r1-distill-llama-70b
fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-llama-70b
gradient_ai/deepseek-r1-distill-llama-70b
nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
novita/deepseek/deepseek-r1-distill-llama-70b
nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
openrouter/deepseek/deepseek-r1-distill-llama-70b
ovhcloud/DeepSeek-R1-Distill-Llama-70B
sambanova/DeepSeek-R1-Distill-Llama-70B
together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B
vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b