Tencent: HY3
tencent/hy3
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings. Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.
Model specifications
- Input
- text
- Output
- text
- Context
- 202,752 tokens
- Max output
- 131,072 tokens
- Input price
- $0.14 / 1M tokens
- Output price
- $0.58 / 1M tokens
- Released
- 2026-07-07
Capabilities
- Streaming
- Function calling
- Vision
- JSON mode
Provider pricing, discounts and data privacy
Compare effective provider prices, published discounts, regions, retention policies, training use, compliance, and privacy links by service tier.
Standard service tier
5 available providers · tier input average $0.1504 / 1M tokens · tier output average $0.6136 / 1M tokens
Tencent Cloud
Tier: Standard
Pricing
- Input
- $0.132 / 1M tokens
- Output
- $0.528 / 1M tokens
- Cache read
- $0.033 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Zero data retention
- Yes
- Data retention
- Unknown retention
- Used for training
- No
- Data collection
- Moderated
- No
- GDPR compliant
- No
- HIPAA compliant
- No
- SOC 2 certified
- No
- BYOK supported
- No
Privacy policy · Terms · Official website · Documentation · Support
DeepInfra
Tier: Standard · Region: US
Pricing
- Input
- $0.14 / 1M tokens
- Output
- $0.58 / 1M tokens
- Cache read
- $0.035 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- US
- Zero data retention
- Yes
- Data retention
- Zero retention
- Used for training
- No
- Data collection
- Moderated
- No
- GDPR compliant
- Yes
- HIPAA compliant
- No
- SOC 2 certified
- Yes
- BYOK supported
- Yes
Privacy policy · Terms · Official website · Documentation · Status · Support
GMICloud
Tier: Standard · Region: US
Pricing
- Input
- $0.14 / 1M tokens
- Output
- $0.58 / 1M tokens
- Cache read
- $0.035 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- US
- Zero data retention
- No
- Data retention
- Unknown retention
- Used for training
- No
- Data collection
- Moderated
- No
- GDPR compliant
- No
- HIPAA compliant
- No
- SOC 2 certified
- Yes
- BYOK supported
- No
Privacy policy · Terms · Official website · Documentation · Support
Novita
Tier: Standard · Region: US
Pricing
- Input
- $0.14 / 1M tokens
- Output
- $0.58 / 1M tokens
- Cache read
- $0.035 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- US
- Zero data retention
- Yes
- Data retention
- Zero retention
- Used for training
- No
- Data collection
- Moderated
- No
- GDPR compliant
- No
- HIPAA compliant
- No
- SOC 2 certified
- No
- BYOK supported
- No
Privacy policy · Terms · Official website · Documentation · Status · Support
AtlasCloud
Tier: Standard · Region: US · Quantization: fp8
Pricing
- Input
- $0.2 / 1M tokens
- Output
- $0.8 / 1M tokens
- Cache read
- $0.05 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- US
- Zero data retention
- No
- Data retention
- 7-day retention
- Used for training
- No
- Data collection
- Moderated
- No
- GDPR compliant
- No
- HIPAA compliant
- No
- SOC 2 certified
- No
- BYOK supported
- No
Privacy policy · Terms · Official website · Documentation · Support
Frequently asked questions
- What is Tencent: HY3?
- Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings. Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.
- How much does Tencent: HY3 cost?
- Input costs start at $0.14 / 1M tokens and output costs start at $0.58 / 1M tokens. Provider-level prices vary by service tier.
- What is the context length of Tencent: HY3?
- Tencent: HY3 supports a 202,752 token context window and up to 131,072 output tokens.
- What capabilities does Tencent: HY3 support?
- Tencent: HY3 supports Streaming, Function calling, Vision, JSON mode.
- Which providers offer Tencent: HY3?
- Tencent: HY3 is available from Tencent Cloud, DeepInfra, GMICloud, Novita, AtlasCloud.
- How do providers handle data privacy for Tencent: HY3?
- 5 of 5 providers report that customer data is not used for training, and 3 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.