DeepSeek

DeepSeek-R1-0528

Vérifié par l’équipe de recherche de GetInfoUsDernière révision : October 2026Politique éditoriale
Raisonnement à Poids OuvertsOfficial Source Verified ↗
52
Intelligence Index

DeepSeek-R1-0528 de DeepSeek est un modèle d’IA conçu pour le raisonnement par chaîne de pensée à poids ouverts et haute efficacité, offrant une fenêtre de contexte de 128K, une vitesse de 48 tokens/s, un indice d’intelligence de 52/100 et un tarif de $0.55/$2.19 par million de tokens.

Technical Specifications

Provider
DeepSeek
Category
reasoning
Release Date
2025-05
Knowledge Cutoff
March 2025
Architecture
Open-Weights Reasoning MoE
Parameters
671B (37B active MoE)
Context Window
128K tokens
Max Output
8K tokens
Cached Input Price
$0.14 / 1M tokens
Batch API Discount
50% off async batch
Consumer Subscription
Free / Self-Hosted
Reasoning Mode
Yes (Chain-of-Thought)
Reasoning Effort Control
Configurable (Low / Med / High)
Tool Calling
Yes
Structured Outputs
Yes
Open Weights
Yes (Open Source / Self-Hostable)
Input Modalities
text
Output Modalities
text
Official Documentation
Visit Official Docs ↗

Data Privacy, Licensing & Deployment Governance

API Data Training Policy
100% Isolated when self-hosted on private GPUs or VPC
Model License & Commercial Rights
Permissive Open-Weights (Apache 2.0 / MIT Commercial)
Deployment & Cloud Availability
Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API
Output Ownership
Full commercial ownership of generated outputs

Official Provider Release Intelligence, API Quotas & Agentic Specs

Compare Multi-Models Side-by-Side →
Official API Model ID (SDK String)
deepseek-reasoner
Supported SDK & API Protocol
OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
Lifecycle & Deprecation Status
Active GA (Guaranteed support through 2027+)
Production Rate Limits (RPM & TPM)
Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
Long-Context Pricing Tier (>128K / >200K)
Flat rate ($0.55/1M in) across full 128K window
Prompt Cache Write & TTL Policy
Automatic prefix caching at $0.14/1M (no extra cache-write fee)
Computer Use & Browser GUI Agent
API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
MCP & Parallel Tool Calling
Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
Web Search Grounding & Code Sandbox
Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
Fine-Tuning & Distillation Support
Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
Multimodal Tokenization Billing
Text BPE (~4 chars/token)
Weights Precision & Quantization
BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
Minimum GPU VRAM Requirement
416 GB VRAM (4-bit Quantized) · 1443 GB VRAM (Native BF16)
Supported Inference Engines
vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
System Card & Safety Framework
Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma)
Enterprise Compliance (SOC2 / HIPAA / ZDR)
100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Engineering & Pricing Workbench

DeepSeek-R1-0528 Cost, Context, Hardware & API Integration

500 / day
4,000 tok
1,000 tok
Conversation Depth (History Re-billing):1 Turn (Single-Shot)
50%
Estimated Monthly API Cost (30 Days)
$53.55$65.85
Monthly Savings: $12.30 (Caching/Batch)
Subscription ($20/mo) vs API

For single-user chat, a $20/mo subscription caps your bill below this API volume.

Break-even point: ~187 requests/day equals $20/month.

Same Monthly Workload Cost Across Popular Reference Models

DeepSeek-R1-0528 (Active)
$53.55
/ month
Gemini 2.5 Flash
$18.00
/ month
DeepSeek V3
$32.70
/ month
GPT-4o
$300.00
/ month
Claude 3.7 Sonnet
$405.00
/ month

Live Prompt Paste Tokenizer & Cost Counter

Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.

Chars / Words
175 / 24
OpenAI o200k
~46 tok
Claude BPE
~49 tok
Llama / DeepSeek
~51 tok

Hybrid Prompt Routing Cascade Simulator

Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to DeepSeek-R1-0528:

Cascaded Monthly Bill:$26.89/mo
Saves $26.66/mo (50% cost reduction) vs sending 100% of traffic to DeepSeek-R1-0528.

Benchmark Scores & 6-Axis Capability Radar

Benchmark Encyclopedia
Coding (60)Reasoning (85)Knowledge (86)Speed (32)Context (75)Cost Value (84)
DeepSeek-R1-05282026 Frontier Median
SWE-bench Verified
51.8%
GPQA Diamond
74.2%
MMLU-Pro
85.6%
HumanEval
92.5%
Humanity's Last Exam
12%
Terminal-Bench
34%
SciCode
31.8%
LiveCodeBench
54%
AIME
85%
Long-Context Reasoning
78%
Chatbot Arena Elo
1355pts

Strengths

  • Fenêtre de contexte de 128K et capacité de sortie maximale de 8K tokens (SWE-bench Verified 51.8% · GPQA Diamond 74.2%)
  • Débit rapide de 48 tokens/seconde avec une latence au premier token (TTFT) de 900 ms
  • Poids ouverts (671B (37B MoE)) permettant un déploiement sur site ou cloud privé via vLLM, SGLang ou Ollama

Limitations & Trade-offs

  • Nécessite des serveurs GPU dotés de suffisamment de mémoire VRAM pour l’inférence locale à pleine précision
  • Sur les problèmes de recherche fondamentale très complexes, les modèles de raisonnement lourd restent supérieurs

Editorial Assessment

Alliant un indice d’intelligence de 52/100, un contexte de 128K et un débit de 48 tok/s, DeepSeek-R1-0528 s’impose comme une valeur sûre de la gamme DeepSeek.

Best for: Conçu pour le raisonnement par chaîne de pensée à poids ouverts et haute efficacité, l’intégration RAG et les pipelines de production évolutifs.

Frequently Asked Questions about DeepSeek-R1-0528

How much does the DeepSeek-R1-0528 API cost per 1M tokens?+

DeepSeek-R1-0528 by DeepSeek is priced at $0.55 per 1M input tokens and $2.19 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.14 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.

Should I use a $20/month subscription or the DeepSeek-R1-0528 pay-as-you-go API?+

A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.

How many words and pages fit in DeepSeek-R1-0528's context window?+

DeepSeek-R1-0528 features a 128K tokens context window, which equals approximately 96,000 English words or ~256 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 8,192 tokens.

Can I run DeepSeek-R1-0528 locally on my own GPU (Open Weights)?+

Yes, DeepSeek-R1-0528 (671B (37B active MoE)) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.

Does DeepSeek train on data sent to the DeepSeek-R1-0528 API, and is commercial use allowed?+

100% Isolated when self-hosted on private GPUs or VPC. License tier: Permissive Open-Weights (Apache 2.0 / MIT Commercial). Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.

How does DeepSeek-R1-0528 perform on coding and reasoning benchmarks?+

DeepSeek-R1-0528 achieves a composite Intelligence Index of 52/100, scoring 51.8% on SWE-bench Verified, 74.2% on GPQA Diamond, 85.6% on MMLU-Pro, and 1355 pts on Chatbot Arena Elo.

What is DeepSeek-R1-0528 best used for?+

DeepSeek-R1-0528 is best suited for: Conçu pour le raisonnement par chaîne de pensée à poids ouverts et haute efficacité, l’intégration RAG et les pipelines de production évolutifs.. Assessment: Alliant un indice d’intelligence de 52/100, un contexte de 128K et un débit de 48 tok/s, DeepSeek-R1-0528 s’impose comme une valeur sûre de la gamme DeepSeek.

Les scores de benchmarks, tarifs par token et limites évoluent rapidement. Vérifiez toujours les spécifications actuelles sur la documentation officielle du fournisseur.

Sources: DeepSeek Technical Report & Model Update (May 2025)↗