The Orchestrator › Models › Tencent
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:...
Specifications
| Provider | Tencent |
| Model ID | tencent/hy3 |
| Context window | 262K tokens (262,144) |
| Modalities | text → text |
| Tokenizer | Other |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway |
| Released | 2026-07-06 |
| Tracked since | 2026-11-14 |
| Popularity | #37 by usage · peak 3.0% spend share in an OpenRouter category |
| Reasoning | On by default |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | tencent/hy3 | $0.132 | $0.528 | 262K |
| standard | TrustedRouter | tencent/hy3 | $0.139 | $0.557 | 262K |
| standard | Vercel AI Gateway | tencent/hy3 | $0.14 | $0.58 | 262K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.14 | $0.58 | 262K |
| 2026-11-14 | $0.139 | $0.557 | 262K |
| 2026-11-14 | $0.132 | $0.528 | 262K |
Capabilities
Agentic tool useStructured outputsReasoning mode256K+ context windowControllable reasoningNo content storage (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, max_completion_tokens, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p