Tencent の Hunyuan TurboS は、超低遅延のリアルタイム対話、高速ルーティング、大量リクエスト処理向けに設計されたAIモデルです。33K のコンテキストウィンドウ、毎秒 160 トークンの生成速度、知能指数 70/100（1Mトークンあたり入力$0.06・出力$0.24）を実現しています。
Technical Specifications
- Provider
- Tencent
- Category
- lightweight
- Release Date
- 2025-03
- Batch API Discount
- 50% off async batch
- Consumer Subscription
- API Pay-as-you-go
- 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)
- hunyuan-turbos
- Supported SDK & API Protocol
- Tencent REST API (OpenAI-Compatible)
- Lifecycle & Deprecation Status
- Active GA (Guaranteed support through 2027+)
- Production Rate Limits (RPM & TPM)
- 5,000 – 15,000 RPM (Production Tier) · 800,000 – 2,000,000 TPM
- Long-Context Pricing Tier (>128K / >200K)
- Flat rate ($0.06/1M in) across full 33K window
- Prompt Cache Write & TTL Policy
- Cached input at $0.006/1M tokens
- 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
- API Prompt Engineering & RAG Distillation
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token)
- Weights Precision & Quantization
- Cloud-Hosted Proprietary (FP8 / BF16 Tensor Core Cluster)
- Minimum GPU VRAM Requirement
- Zero Local VRAM Required (100% Serverless Cloud API)
- Supported Inference Engines
- Managed Tencent Cloud API
- System Card & Safety Framework
- Tencent Production Safety & Alignment Verified
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- SOC2 Type II · GDPR · Zero Data Retention (ZDR) & HIPAA BAA Available on Enterprise Tier
Hunyuan TurboS Cost, Context, Hardware & API Integration
Pay-as-you-go API is cheaper for this volume (saves $14.42/mo vs $20 flat plan).
Break-even point: ~1,792 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 Hunyuan TurboS:
Benchmark Scores & 6-Axis Capability Radar
- MMLU-Pro
- 67%
- HumanEval
- 76%
- Chatbot Arena Elo
- 1225pts
Strengths
- 33K のコンテキストウィンドウと最大 4K トークンの出力容量（MMLU-Pro 67% · Arena Elo 1225）
- 毎秒 160 トークンの高速スループットと、初回トークン到達時間（TTFT）わずか 250ms の低遅延
- 優れたAPI経済性（1Mトークンあたり入力$0.06・出力$0.24）に加え、プロンプトキャッシュや構造化JSON出力・関数呼び出しに完全対応
Limitations & Trade-offs
- クラウド専用のプロプライエタリモデルのため、モデル重みをダウンロードしてオフライン実行することはできません
- 極めて高度な専門科学の証明問題では、上位の大型推論特化モデルの方がより深い洞察を提供する場合があります
Editorial Assessment
知能指数 70/100、33K コンテキスト、毎秒 160 トークンの速度を兼ね備えた Hunyuan TurboS は、Tencent のラインナップにおいて非常に実用性の高い主力モデルです。
Best for: 超低遅延のリアルタイム対話、高速ルーティング、大量リクエスト処理、エンタープライズRAG基盤、スケーラブルな本番API統合に最適。
Compare Hunyuan TurboS
Frequently Asked Questions about Hunyuan TurboS
How much does the Hunyuan TurboS API cost per 1M tokens?+
Hunyuan TurboS by Tencent is priced at $0.06 per 1M input tokens and $0.24 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.006 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.
Should I use a $20/month subscription or the Hunyuan TurboS 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 Hunyuan TurboS's context window?+
Hunyuan TurboS features a 33K tokens context window, which equals approximately 24,576 English words or ~66 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 4,096 tokens.
Can I run Hunyuan TurboS locally on my own GPU (Open Weights)?+
No, Hunyuan TurboS is a proprietary closed-weights model hosted by Tencent. It cannot be downloaded for local GPU execution and must be accessed via Tencent's official API or cloud platform.
Does Tencent train on data sent to the Hunyuan TurboS API, and is commercial use allowed?+
API payloads are excluded from model training by default. License tier: Proprietary Commercial API (Tencent Terms). Full commercial ownership of generated outputs. Supported deployment channels include: Tencent Cloud API & Enterprise Endpoints.
How does Hunyuan TurboS perform on coding and reasoning benchmarks?+
Hunyuan TurboS achieves a composite Intelligence Index of 70/100, scoring N/A% on SWE-bench Verified, N/A% on GPQA Diamond, 67% on MMLU-Pro, and 1225 pts on Chatbot Arena Elo.
What is Hunyuan TurboS best used for?+
Hunyuan TurboS is best suited for: 超低遅延のリアルタイム対話、高速ルーティング、大量リクエスト処理、エンタープライズRAG基盤、スケーラブルな本番API統合に最適。. Assessment: 知能指数 70/100、33K コンテキスト、毎秒 160 トークンの速度を兼ね備えた Hunyuan TurboS は、Tencent のラインナップにおいて非常に実用性の高い主力モデルです。
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 Hunyuan TurboS:
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.