The Orchestrator › Models › Tencent
Tencent: Hy4
The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...
Specifications
| Provider | Tencent |
| Model ID | tencent/hy4 |
| Context window | 1.0M tokens (1,048,576) |
| Modalities | text + image → text |
| Tokenizer | Other |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway |
| Released | 2026-11-04 |
| Tracked since | 2026-11-14 |
| Popularity | #24 by usage · peak 5.9% spend share in an OpenRouter category |
| Reasoning | On by default |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | tencent/hy4 | $0.417 | $1.25 | 1.0M |
| standard | TrustedRouter | tencent/hy4 | $0.44 | $1.32 | 1M |
| standard | Vercel AI Gateway | tencent/hy4 | $0.417 | $1.25 | 1.0M |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.417 | $1.25 | 1.0M |
| 2026-11-14 | $0.44 | $1.32 | 1M |
| 2026-11-14 | $0.417 | $1.25 | 1.0M |
Capabilities
Vision (image input)Agentic tool useStructured outputsReasoning mode1M+ context windowControllable reasoningNo content storage (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, stop, structured_outputs, temperature, tool_choice, tools