DeepSeek

DeepSeek Reasoner

Vérifié par l’équipe de recherche de GetInfoUsDernière révision : October 2026Politique éditoriale
Raisonneur open sourceOfficial Source Verified ↗
54
Intelligence Index

1-millions-token ouvert raisonnement centrale développé pour multi-étapes mathematics, complexe codage, et structuré outil usage.

Technical Specifications

Provider
DeepSeek
Category
reasoning
Release Date
2025-12
Knowledge Cutoff
September 2025
Architecture
Reinforcement-Learned Reasoning MoE
Parameters
671B Total (37B Active)
Context Window
1M tokens
Max Output
33K tokens
Cached Input Price
$0.028 / 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 ($0.28/1M in) across full 1000K window
Prompt Cache Write & TTL Policy
Automatic prefix caching at $0.028/1M (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 Reasoner 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)
$15.54$23.10
Monthly Savings: $7.56 (Caching/Batch)
Subscription ($20/mo) vs API

Pay-as-you-go API is cheaper for this volume (saves $4.46/mo vs $20 flat plan).

Break-even point: ~644 requests/day equals $20/month.

Same Monthly Workload Cost Across Popular Reference Models

DeepSeek Reasoner (Active)
$15.54
/ 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 Reasoner:

Cascaded Monthly Bill:$17.39/mo
This model is already priced at or below the fast router baseline.

Benchmark Scores & 6-Axis Capability Radar

Benchmark Encyclopedia
Coding (65)Reasoning (88)Knowledge (86)Speed (35)Context (100)Cost Value (94)
DeepSeek Reasoner2026 Frontier Median
SWE-bench Verified
56.5%
GPQA Diamond
76.5%
MMLU-Pro
86.2%
HumanEval
93.4%
Humanity's Last Exam
13.5%
Terminal-Bench
37.5%
SciCode
35%
LiveCodeBench
58.5%
AIME
87.5%
Long-Context Reasoning
85%
Chatbot Arena Elo
1368pts

Strengths

  • étendu 1M contexte capacité combined avec rigorous chaîne de pensée logique
  • inégalé tarification disruption: seulement $0.28 entrée et $0.42 sortie par millions tokens
  • élevé précision sur STEM benchmarks, AIME, et complexe programmation challenges

Limitations & Trade-offs

  • Highly verbose responses qui peut consume significant sortie quota if pas constrained
  • texte-seulement entrée modality sans diagram ou document image support

Editorial Assessment

le ultimate économique-conscious raisonnement moteur, fournissant 1M-contexte logical profondeur à fractional API coûts.

Best for: au format long code audits, mathématique analyse, et économique-friendly autonome raisonnement boucles

Frequently Asked Questions about DeepSeek Reasoner

How much does the DeepSeek Reasoner API cost per 1M tokens?+

DeepSeek Reasoner by DeepSeek is priced at $0.28 per 1M input tokens and $0.42 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.028 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.

Should I use a $20/month subscription or the DeepSeek Reasoner 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 Reasoner's context window?+

DeepSeek Reasoner features a 1M tokens context window, which equals approximately 750,000 English words or ~2,000 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 32,768 tokens.

Can I run DeepSeek Reasoner locally on my own GPU (Open Weights)?+

Yes, DeepSeek Reasoner (671B Total (37B Active)) 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 Reasoner 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 Reasoner perform on coding and reasoning benchmarks?+

DeepSeek Reasoner achieves a composite Intelligence Index of 54/100, scoring 56.5% on SWE-bench Verified, 76.5% on GPQA Diamond, 86.2% on MMLU-Pro, and 1368 pts on Chatbot Arena Elo.

What is DeepSeek Reasoner best used for?+

DeepSeek Reasoner is best suited for: au format long code audits, mathématique analyse, et économique-friendly autonome raisonnement boucles. Assessment: le ultimate économique-conscious raisonnement moteur, fournissant 1M-contexte logical profondeur à fractional API coûts.

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

Sources: DeepSeek Reasoner API Specifications (December 2025)↗