Tencent: Hy4 preview
Try Hy4 preview on us. Starter credit covers your first requests, then one key reaches all 4 provider routes with automatic failover.
tencent/hy4-preview
| Publisher | Tencent Cloud TokenHubtencent |
|---|---|
| AI IQ | IQ 113 #63 on AI IQ |
| Context | 1,000,000 tokens |
| Providers | |
| Credits routes | 4 provider routes |
| Modes | chat open weights US providers EU-focused |
| Billing | Credits |
Current route evidence
Live leaderboardRecent provider-route uptime spans not enough data across 4 routes and 4 providers. Price comes from the current Credits catalog. Speed and uptime come from routed probes rather than vendor claims.
Providers serving this model
Sorted by lowest combined prompt and completion price. Use
"provider": {"sort": "throughput"} in the request body
(or append :nitro to the model id) to route to the
fastest provider instead.
Trust boundary: TR router attestation verifies the TrustedRouter gateway only. Provider policy separately describes the upstream model host's retention, confidential compute, and E2EE posture.
| Provider | Input | Cached input | Output | Weight format | TR router attested | Provider policy |
|---|---|---|---|---|---|---|
| DeepInfradeepinfra | $0.87987/1M | $0.04431/1M | $2.638555/1M | Unknown | yes | no verified privacy claim |
| GMI Cloudgmi | $0.87987/1M | $0.04431/1M | $2.638555/1M | Unknown | yes | privacy unknown |
| Novita AInovita | $0.87987/1M | $0.04431/1M | $2.638555/1M | Unknown | yes | privacy unknown |
| Tencent Cloud TokenHubtencent | $0.87987/1M | $0.04431/1M | $2.638555/1M | Unknown | yes | privacy unknown |
Endpoint JSON: https://api-azure.trustedrouter.com/v1/models/tencent/hy4-preview/endpoints
Compare Tencent: Hy4 preview
All comparisons- Tencent: Hy4 preview vs Z.ai: GLM 5.337 combined provider routes
- Tencent: Hy4 preview vs Z.ai: GLM 5.236 combined provider routes
- Tencent: Hy4 preview vs Z.ai: GLM 5.3 Flash36 combined provider routes
- MoonshotAI: Kimi K3 vs Tencent: Hy4 preview32 combined provider routes
- DeepSeek: DeepSeek V4 Flash 0731 vs Tencent: Hy4 preview30 combined provider routes
- DeepSeek: DeepSeek V4.1 Flash vs Tencent: Hy4 preview28 combined provider routes
Questions
What model ID should I use for Tencent: Hy4 preview?
Use tencent/hy4-preview as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.
Which providers serve Tencent: Hy4 preview?
TrustedRouter currently lists Novita AI, GMI Cloud, Tencent Cloud TokenHub, and DeepInfra for Tencent: Hy4 preview. Provider availability and routing eligibility can change as catalog and health data update.
How much does Tencent: Hy4 preview cost through TrustedRouter?
The current lowest Credits input price is $0.87987/1M and the lowest Credits output price is $2.638555/1M. Prices are per one million tokens and come from the current route catalog.
How do I require zero data retention for Tencent: Hy4 preview?
Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.