O DeepSeek-Coder-V2 236B da DeepSeek é um modelo de IA projetado para auto-hospedagem em infraestrutura própria, fine-tuning e soberania de dados, oferecendo janela de contexto de 128K, velocidade de 74 tokens/s, índice de inteligência de 42/100 e tarifa de $0.14/$0.28 por 1M de tokens.
Technical Specifications
- Provider
- DeepSeek
- Category
- open-source
- Release Date
- 2024-06
- Batch API Discount
- 50% off async batch
- Consumer Subscription
- Free / Self-Hosted
- Reasoning Effort Control
- Fixed
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- deepseek-chat
- Supported SDK & API Protocol
- OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
- Lifecycle & Deprecation Status
- Legacy Stable (Upgrade path available in DeepSeek lineup)
- 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 ($0.14/1M in) across full 128K window
- Prompt Cache Write & TTL Policy
- Automatic prefix caching at $0.014/1M (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
- 146 GB VRAM (4-bit Quantized) · 507 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
DeepSeek-Coder-V2 236B Cost, Context, Hardware & API Integration
Pay-as-you-go API is cheaper for this volume (saves $11.18/mo vs $20 flat plan).
Break-even point: ~1,134 requests/day equals $20/month.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to DeepSeek-Coder-V2 236B:
Benchmark Scores & 6-Axis Capability Radar
- SWE-bench Verified
- 42.1%
- GPQA Diamond
- 49.5%
- MMLU-Pro
- 69.8%
- HumanEval
- 90.2%
- Humanity's Last Exam
- 5.8%
- Terminal-Bench
- 27.8%
- SciCode
- 29.4%
- LiveCodeBench
- 48.6%
- AIME
- 61.2%
- Long-Context Reasoning
- 66.5%
- Chatbot Arena Elo
- 1272pts
Strengths
- Janela de contexto de 128K com limite máximo de saída de 8K tokens (SWE-bench Verified 42.1% · GPQA Diamond 49.5%)
- Taxa de transferência rápida de 74 tokens/segundo com latência inicial (TTFT) de 510 ms
- Pesos abertos (236B) para auto-hospedagem local ou em nuvem privada via vLLM, SGLang ou Ollama
Limitations & Trade-offs
- Requer servidores GPU com memória VRAM adequada para execução local em precisão total
- Em derivações científicas extremas, modelos pesados dedicados exclusivamente ao raciocínio oferecem maior profundidade
Editorial Assessment
Combinando índice de inteligência de 42/100, contexto de 128K e 74 tok/s, o DeepSeek-Coder-V2 236B entrega excelente equilíbrio entre desempenho e custo no portfólio da DeepSeek.
Best for: Indicado para auto-hospedagem em infraestrutura própria, fine-tuning e soberania de dados, arquiteturas RAG corporativas e integração escalável via API.
Compare DeepSeek-Coder-V2 236B
Frequently Asked Questions about DeepSeek-Coder-V2 236B
How much does the DeepSeek-Coder-V2 236B API cost per 1M tokens?+
DeepSeek-Coder-V2 236B by DeepSeek is priced at $0.14 per 1M input tokens and $0.28 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.014 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.
Should I use a $20/month subscription or the DeepSeek-Coder-V2 236B 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-Coder-V2 236B's context window?+
DeepSeek-Coder-V2 236B 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-Coder-V2 236B locally on my own GPU (Open Weights)?+
Yes, DeepSeek-Coder-V2 236B (236B) 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-Coder-V2 236B 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-Coder-V2 236B perform on coding and reasoning benchmarks?+
DeepSeek-Coder-V2 236B achieves a composite Intelligence Index of 42/100, scoring 42.1% on SWE-bench Verified, 49.5% on GPQA Diamond, 69.8% on MMLU-Pro, and 1272 pts on Chatbot Arena Elo.
What is DeepSeek-Coder-V2 236B best used for?+
DeepSeek-Coder-V2 236B is best suited for: Indicado para auto-hospedagem em infraestrutura própria, fine-tuning e soberania de dados, arquiteturas RAG corporativas e integração escalável via API.. Assessment: Combinando índice de inteligência de 42/100, contexto de 128K e 74 tok/s, o DeepSeek-Coder-V2 236B entrega excelente equilíbrio entre desempenho e custo no portfólio da DeepSeek.
DeepSeek Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to DeepSeek's flagship reasoning tier:
DeepSeek V4.1-Flash
DeepSeek V4 Pro
DeepSeek V4
DeepSeek Reasoner
DeepSeek Chat
DeepSeek-R1-0528
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to DeepSeek-Coder-V2 236B:
The basic unit of text that a language model processes, typically representing about 3 to 4 English characters or roughly 0.75 words. For example, the sentence "Artificial intelligence is fast" breaks down into about 5 tokens.
A standardized evaluation suite used to objectively measure and rank an AI model's capabilities across specific tasks — such as SWE-bench Verified for software engineering, AIME for competitive math, or MMLU for general knowledge.
The maximum number of tokens a model can consider at once — both the input it reads and the output it writes. A 1,000,000-token context window can hold roughly 750,000 English words in a single request.
The ability of a language model to recognize when an external capability is needed and output structured JSON arguments to invoke external APIs, databases, or terminal commands. The runtime executes the tool and passes results back to the model.
An open standard created by Anthropic that allows AI applications and agents to connect seamlessly to local filesystems, development environments, and third-party APIs via standardized server interfaces.
A cost and latency optimization where inference providers store pre-computed attention states for repeated prompt prefixes. Reusing cached tokens typically slashes API input costs by 50% to 90% and cuts TTFT substantially.
Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.
Fontes oficiais: DeepSeek Official Platform Documentation & Pricing↗