DeepSeek logo

DeepSeek R1 528

Deprecated
Pricing & Specs API
Free REST API for prices, specs and benchmarks
DeepSeek R1 528 is DeepSeek's language model with a 164K context window and up to 33K output tokens, available from 10 providers, starting at $0.2 / 1M input and $0.25 / 1M output. The DeepSeek R1 0528 update, a reasoning-focused MoE LLM with improved chain-of-thought capabilities over the original R1 release.
Specifications
Canonical IDdeepseek-r1-528
TypeLanguage
StatusDeprecated
CreatorDeepSeekDeepSeek
Providers
Context Window164K tokens
Max Output33K tokens
Input ModalitiesPDFText
Output ModalitiesText
Reasoning Effortsdefault
Parameters685B
HuggingFace Likes2,445
HuggingFace Downloads (30d)707,890
HuggingFace Downloads (all-time)6,472,632
Release Date · 1 year ago
Knowledge Cutoff · 2 years ago
Deprecation Date

Capabilities

Input2/5
Text✓
Image·
Audio·
Video·
PDF✓
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities7/13
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
ProviderStandardBatch
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Input
$ / 1M
Output
$ / 1M
Crusoe
crusoe/deepseek-ai/DeepSeek-R1-0528
$3.00$7.00N/A——
DeepInfra logo
DeepInfra
deepinfra/deepseek-ai/DeepSeek-R1-0528
$0.5$2.15$0.4——
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/deepseek-r1-0528
$3.00$8.00N/A——
Google Vertex AI logo
Google Vertex AI
deepseek-r1-0528
$1.35$5.40N/A$0.675$2.70
Hugging Face logo
Hugging Face
novita:deepseek/deepseek-r1-0528
$0.7$2.50N/A——
Hyperbolic logo
Hyperbolic
hyperbolic/deepseek-ai/DeepSeek-R1-0528
$0.25$0.25N/A——
Lambda logo
Lambda
lambda_ai/deepseek-r1-0528
$0.2$0.6N/A——
Novita logo
Novita
novita/deepseek/deepseek-r1-0528
$0.7$2.50$0.35——
OpenRouter logo
OpenRouter
deepseek/deepseek-r1-0528
$0.5$2.15$0.35——
Together AI logo
Together AI
together_ai/deepseek-ai/DeepSeek-R1-0528
$3.00$7.00N/A——

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host DeepSeek R1 528, ranked by cheapest on-demand price. The model needs about 1643 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
p6-b300.48xlargeAWS8× B3002149 GB$142.42/hr

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
DeepSeek R1T2 Chimera164K——Available
DeepSeek R1 528164K$0.200$0.250Current
DeepSeek R1 Distill Qwen 32B131K$0.150$0.150Available
DeepSeek R1 Distill Llama 70B131K$0.200$0.375Deprecated
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-r1-0528
crusoe/deepseek-ai/DeepSeek-R1-0528
deepinfra/deepseek-ai/DeepSeek-R1-0528
deepseek-ai/DeepSeek-R1-0528
deepseek-llm-r1-0528
deepseek-r1-0528
deepseek-r1-0528-maas
deepseek-r1-528
deepseek/deepseek-r1-0528
fireworks_ai/accounts/fireworks/models/deepseek-r1-0528
hyperbolic/deepseek-ai/DeepSeek-R1-0528
lambda_ai/deepseek-r1-0528
nebius/deepseek-ai/DeepSeek-R1-0528
novita/deepseek/deepseek-r1-0528
openrouter/deepseek/deepseek-r1-0528
publishers/google/models/deepseek-r1-0528-maas
together_ai/deepseek-ai/DeepSeek-R1-0528
vertex_ai/deepseek-ai/deepseek-r1-0528-maas
wandb/deepseek-ai/DeepSeek-R1-0528