Tencent's fast, low-cost Hy4 tier: a 224B-parameter MoE with 12B active parameters, multimodal input and a 1M context window, built for high-volume coding, agentic and everyday workloads.
hy4-flashCompare price, limits and live performance side by side. LLM Gateway routes each request to the best provider that can handle your prompt size and parameters.
1 provider
| Provider | Actions | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| 1M | 65.5k | $0.07 | $0.281 | $0.003 |
Prices are per provider at standard rates; open a row for regions, tiers and cache pricing. Throughput, latency and uptime come from LLM Gateway traffic over the last 24 hours and are hidden under 1,000 requests.
Tencent's fast, low-cost Hy4 tier: a 224B-parameter MoE with 12B active parameters, multimodal input and a 1M context window, built for high-volume coding, agentic and everyday workloads. You can access it through LLM Gateway's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Hy4 Flash on LLM Gateway starts at $0.07 per million input tokens and $0.28 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Hy4 Flash supports a context window of up to 1,000,000 tokens on its largest provider deployment.
Hy4 Flash is served by Tencent Cloud through LLM Gateway. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Yes. Hy4 Flash supports both tool (function) calling and strict JSON output schema (upstream-enforced) through LLM Gateway.
Hy4 Flash was released on November 16, 2026.