Hy3 Preview
by TencentChat
Tencent Hy reasoning model for coding, instruction following, and agent tasks
- Context
- 262K tokens
- Max output
- 235,929 tokens
- Parameters
- 299B total, 21B active
- Released
- 2026-04-20
- Weights
- Open
- Licence
- tencent-hy-community
tencent/hy3-preview · also seen as tencent/hy3-preview-20260421
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2026-04-20
- Weights
- Opennot gated
- License
- tencent-hy-community
- Input
- Text
- Output
- Text
- Context window
- 262,144 max across endpoints
- Max output
- 235,929
- Providers
- 2 + 4 gateways, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.18 in · $0.60 out per 1M tokens · 1 of 2 providers have a comparable price
More details
- Last updated
- 2026-04-20
- Knowledge cutoff
- Weights link
- Hugging Face · tencent/Hy3-preview
- Parameters
- 299B total, 21B active
- Developer country
- China
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt caching
- Web searchunknown
- Computer useunknown
- System messagesunknown
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
No change since 19 Oct 2026. The cheapest direct price has been $0.18 in / $0.60 out per 1M tokens at GMI Cloud on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Hy3 Preview |
|---|---|---|---|---|---|
| DeepSeek V3.2 ExpDeepSeek | $0.238 | $0.22 | $0.33 | 164K | +1% |
| Qwen3-Next 80B-A3B (Thinking)Alibaba (Qwen) | $0.233 | $0.15 | $0.65 | 131K | −1% cheaper |
| Qwen3.8-27BAlibaba (Qwen) | $0.242 | $0.15 | $0.70 | 1M | +2% |
| Gemini 3.1 Flash Lite PreviewGoogle | $0.229 | $0.125 | $0.75 | 1.05M | −3% cheaper |
| Qwen3.5 122B-A10BAlibaba (Qwen) | $0.244 | $0.113 | $0.901 | 262K | +3% |
| Qwen3.6 35B-A3BAlibaba (Qwen) | $0.227 | $0.112 | $0.80 | 262K | −4% cheaper |
| deepseek-v3.2DeepSeek | $0.226 | $0.209 | $0.31 | 164K | −4% cheaper |
| Qwen 3 Coder 30B A3B InstructAlibaba (Qwen) | $0.225 | $0.15 | $0.60 | 262K | −5% cheaper |
More from Tencent
Newest Tencent models in the catalogue. All Tencent models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Hy Image 3.5 Preview | 2026-10-05 | 100K | unpriced |
| Hy4 preview | 2026-08-28 | 1.05M | from $0.67 |
| Hy-MT2-1.8B | 2026-08-20 | 8.2K | from $0.044 |
| Hy-MT2-30B-A3B | 2026-08-20 | 8.2K | from $0.074 |
| Hy-MT2-7B | 2026-08-19 | 8.2K | from $0.074 |
| Hy3 | 2026-07-06 | 262K | from $0.132 |
| Tencent Hy-MT2-Lite | 2026-06-12 | 8K | $0.044 via Vercel AI Gateway |
| Tencent Hy-MT2-Pro | 2026-05-21 | 8K | $0.074 via Vercel AI Gateway |