Tencent tarafından geliştirilen Hy3, 262K token bağlam penceresi ve 1M girdi başına $0, 1M çıktı başına $0 API fiyatlandırmasıyla yazılım geliştirme, analiz ve kurumsal otomasyon için tasarlanmıştır.
Technical Specifications
- Provider
- Tencent
- Category
- open-source
- Release Date
- 2026-07
- Batch API Discount
- Standard rate
- Consumer Subscription
- Free / Self-Hosted
- Reasoning Effort Control
- Configurable (Low / Med / High)
- 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)
- hy3
- Supported SDK & API Protocol
- OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
- Lifecycle & Deprecation Status
- Active GA (Guaranteed support through 2028+)
- 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)
- Free across full context window (only KV-cache VRAM scales)
- Prompt Cache Write & TTL Policy
- Automatic prefix KV-caching in vLLM / SGLang (0 cost)
- 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
- 87 GB VRAM (4-bit Quantized) · 301 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
Hy3 Cost, Context, Hardware & API Integration
Open-weights or free-tier model: $0 API license cost when self-hosted.
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 Hy3:
Benchmark Scores & 6-Axis Capability Radar
- GPQA Diamond
- 64%
- MMLU-Pro
- 79%
- HumanEval
- 88%
- Chatbot Arena Elo
- 1330pts
Strengths
- Tencent imzalı gelişmiş Efficient Open Reasoning MoE Transformer mimarisi ve 262K token bağlam kapasitesi
- Dengeli API maliyeti ($0/1M girdi, $0/1M çıktı) ve yüksek yanıt hızı
- Kod üretimi, mantıksal çıkarım ve çok dilli görevlerde güçlü kıyaslama (benchmark) sonuçları
Limitations & Trade-offs
- Çok uzun bağlamlı sorgularda token maliyetlerinin dikkatli yönetilmesi gerekir
- Alan bazlı özel iş akışlarında en yüksek verim için doğru istem (prompt) tasarımı önerilir
Editorial Assessment
Hy3, Tencent ekosisteminde performans, hız ve maliyet dengesini başarıyla sunan güvenilir bir modeldir.
Best for: Kurumsal otomasyon, yazılım mühendisliği, otonom YZ ajanları ve Tencent tabanlı üretim sistemleri
Compare Hy3
Frequently Asked Questions about Hy3
How much does the Hy3 API cost per 1M tokens?+
Hy3 by Tencent is priced at $0 per 1M input tokens and $0 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0 per 1M tokens, and asynchronous Batch API requests receive a 0% discount.
Should I use a $20/month subscription or the Hy3 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 Hy3's context window?+
Hy3 features a 262K tokens context window, which equals approximately 196,608 English words or ~524 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 16,384 tokens.
Can I run Hy3 locally on my own GPU (Open Weights)?+
Yes, Hy3 (Confidential / 140B MoE) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.
Does Tencent train on data sent to the Hy3 API, and is commercial use allowed?+
100% Isolated when self-hosted on private GPUs or VPC. License tier: Open-Weights Research & Commercial License. Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.
How does Hy3 perform on coding and reasoning benchmarks?+
Hy3 achieves a composite Intelligence Index of 81/100, scoring N/A% on SWE-bench Verified, 64% on GPQA Diamond, 79% on MMLU-Pro, and 1330 pts on Chatbot Arena Elo.
What is Hy3 best used for?+
Hy3 is best suited for: Kurumsal otomasyon, yazılım mühendisliği, otonom YZ ajanları ve Tencent tabanlı üretim sistemleri. Assessment: Hy3, Tencent ekosisteminde performans, hız ve maliyet dengesini başarıyla sunan güvenilir bir modeldir.
Tencent Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to Tencent's flagship reasoning tier:
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to Hy3:
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.
An AI model trained via reinforcement learning to spend dynamic compute thinking through complex logic, math, and architectural problems before outputting a solution. Examples include OpenAI o1, o3, and DeepSeek R1.
A step-by-step reasoning technique where an AI model generates intermediate problem-solving thoughts before arriving at a final answer. Native reasoning models like OpenAI o3 and DeepSeek R1 use CoT to solve complex math and coding challenges.
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.
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.
Resmi kaynaklar: Tencent Open Source & Hugging Face↗