Tencent

Hy3 preview

Vérifié par l’équipe de recherche de GetInfoUsDernière révision : October 2026Politique éditoriale
Modèle de Base à Poids OuvertsOfficial Source Verified ↗
79
Intelligence Index

Hy3 preview de Tencent est un modèle d’IA conçu pour l’auto-hébergement sur infrastructure privée, le fine-tuning et la souveraineté des données, offrant une fenêtre de contexte de 262K, une vitesse de 88 tokens/s, un indice d’intelligence de 79/100 et un tarif de accès gratuit à poids ouverts.

Technical Specifications

Provider
Tencent
Category
open-source
Release Date
2026-04
Knowledge Cutoff
February 2026
Architecture
Preview Open Reasoning MoE Transformer
Parameters
Confidential / 140B MoE
Context Window
262K tokens
Max Output
8K tokens
Cached Input Price
$0 / 1M tokens
Batch API Discount
Standard rate
Consumer Subscription
Free / Self-Hosted
Reasoning Mode
Yes (Chain-of-Thought)
Reasoning Effort Control
Fixed
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
Open-Weights Research & Commercial License
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)
hy3-preview
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
Engineering & Pricing Workbench

Hy3 preview 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)
Free ($0)
Subscription ($20/mo) vs API

Open-weights or free-tier model: $0 API license cost when self-hosted.

Same Monthly Workload Cost Across Popular Reference Models

Hy3 preview (Active)
$0.00
/ 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 Hy3 preview:

Cascaded Monthly Bill:$13.50/mo
This model is already priced at or below the fast router baseline.

Benchmark Scores & 6-Axis Capability Radar

Benchmark Encyclopedia
Coding (85)Reasoning (79)Knowledge (77)Speed (59)Context (85)Cost Value (98)
Hy3 preview2026 Frontier Median
MMLU-Pro
76.5%
HumanEval
85%
Chatbot Arena Elo
1310pts

Strengths

  • Fenêtre de contexte de 262K et capacité de sortie maximale de 8K tokens (MMLU-Pro 76.5% · Arena Elo 1310)
  • Débit rapide de 88 tokens/seconde avec une latence au premier token (TTFT) de 440 ms
  • Poids ouverts (Confidential / 140B 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 79/100, un contexte de 262K et un débit de 88 tok/s, Hy3 preview s’impose comme une valeur sûre de la gamme Tencent.

Best for: Conçu pour l’auto-hébergement sur infrastructure privée, le fine-tuning et la souveraineté des données, l’intégration RAG et les pipelines de production évolutifs.

Frequently Asked Questions about Hy3 preview

How much does the Hy3 preview API cost per 1M tokens?+

Hy3 preview 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 preview 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 preview's context window?+

Hy3 preview 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 8,192 tokens.

Can I run Hy3 preview locally on my own GPU (Open Weights)?+

Yes, Hy3 preview (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 preview 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 preview perform on coding and reasoning benchmarks?+

Hy3 preview achieves a composite Intelligence Index of 79/100, scoring N/A% on SWE-bench Verified, N/A% on GPQA Diamond, 76.5% on MMLU-Pro, and 1310 pts on Chatbot Arena Elo.

What is Hy3 preview best used for?+

Hy3 preview is best suited for: Conçu pour l’auto-hébergement sur infrastructure privée, le fine-tuning et la souveraineté des données, l’intégration RAG et les pipelines de production évolutifs.. Assessment: Alliant un indice d’intelligence de 79/100, un contexte de 262K et un débit de 88 tok/s, Hy3 preview s’impose comme une valeur sûre de la gamme Tencent.

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:

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

Sources: Tencent Hunyuan Research Hub↗