Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for tencent

Tencent: Hy3 preview

tencent/hy3-preview

Model weights
Compare

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to balance speed and depth depending on the task, while delivering strong code generation and reliable performance across multi-step, real-world workflows.

Modalities
In / Out Price
$0.18 / $0.60per 1M
Context
262K
Released
Apr 22, 2026
Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Tencent: Hy3 preview (Artificial Analysis)
SourceBenchmarkScore
Artificial AnalysisHy3-preview (Non-reasoning) GPQA Diamond73.2%
Artificial AnalysisHy3-preview (Non-reasoning) HLE7.0%
Artificial AnalysisHy3-preview (Non-reasoning) IFBench48.0%
Artificial AnalysisHy3-preview (Non-reasoning) τ²-Bench Telecom67.5%
Artificial AnalysisHy3-preview (Non-reasoning) AA-LCR42.0%
Artificial AnalysisHy3-preview (Non-reasoning) CritPt0.3%
Artificial AnalysisHy3-preview (Non-reasoning) Terminal-Bench Hard31.8%
Artificial AnalysisHy3-preview (Non-reasoning) AA-Omniscience Accuracy23.2%
Artificial AnalysisHy3-preview (Non-reasoning) AA-Omniscience Non-Hallucination Rate24.3%
Artificial AnalysisHy3 Intelligence Index25.3
Artificial AnalysisHy3 Coding Index58.8
Artificial AnalysisHy3 Agentic Index24.1
Artificial AnalysisHy3 GPQA Diamond89.7%
Artificial AnalysisHy3 HLE33.5%
Artificial AnalysisHy3 AA-LCR79.0%
Artificial AnalysisHy3 GDPval-AA27.3%
Artificial AnalysisHy3 CritPt4.9%
Artificial AnalysisHy3 SciCode48.6%
Artificial AnalysisHy3 AA-Omniscience Accuracy32.0%
Artificial AnalysisHy3 AA-Omniscience Non-Hallucination Rate25.9%
Artificial AnalysisHy3-preview (Reasoning) GPQA Diamond86.7%
Artificial AnalysisHy3-preview (Reasoning) HLE27.8%
Artificial AnalysisHy3-preview (Reasoning) IFBench63.1%
Artificial AnalysisHy3-preview (Reasoning) τ²-Bench Telecom92.7%
Artificial AnalysisHy3-preview (Reasoning) AA-LCR64.7%
Artificial AnalysisHy3-preview (Reasoning) CritPt4.6%
Artificial AnalysisHy3-preview (Reasoning) Terminal-Bench Hard34.1%
Artificial AnalysisHy3-preview (Reasoning) AA-Omniscience Accuracy27.9%
Artificial AnalysisHy3-preview (Reasoning) AA-Omniscience Non-Hallucination Rate12.6%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Model RankingsRanking
$0.18$0.60$0.062.59s71 tps
100.00%
Throughput
71tok/s

P50, best across providers

Latency
2.59s

P50, best provider

Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.70%

Availability over the last 3 days

Last 72 hours
Availability 99.70%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.74%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

1.
Favicon for https://buddypro.ai/
BuddyPro AI
Build profitable AI digital twin from know-how in 3 days
6.45Btokens
2.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
3.14Btokens
3.
Favicon for https://openclaw.ai/
OpenClaw
OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.
587Mtokens
4.
Favicon for https://kilocode.ai/
Kilo Code
Kilo Code is an open-source AI coding agent that works across VS Code, JetBrains, and CLI to help developers ship code faster with agentic workflows.
308Mtokens
5.
Favicon for https://agent.strikingly.com/
Strikingly AI Agent
new
152Mtokens

Frequently asked questions

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to balance speed and depth depending on the task, while delivering strong code generation and reliable performance across multi-step, real-world workflows.

Hy3 preview costs $0.18/M input tokens and $0.60/M output tokens, with separate rates for Cache Read at $0.06/M tokens.

Hy3 preview has a 262,144 token context window.

Yes. Hy3 preview accepts tools and tool_choice for function calling. It does not support response_format, so JSON output is not enforced.

Hy4 preview, Hy-MT2-1.8B, Hy-MT2-30B-A3B and 3 more are other text models from Tencent.

Hy3 preview was released on April 22, 2026.

More models from tencent

Hy4 preview

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that require planning, context continuity, and sustained multi-step execution.

Text1.0M context$0.834 / $2.501
Hy-MT2-1.8B

Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.

Text8K context$0.044 / $0.177
Hy-MT2-30B-A3B

Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation. It uses 3B active parameters out of 30B total.

Text8K context$0.074 / $0.295
Hy-MT2-7B

Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.

Text8K context$0.074 / $0.295
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: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.

Tencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.

Text262K context$0.13 / $0.53
Hunyuan A13B Instruct

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark performance across mathematics, science, coding, and multi-turn reasoning tasks, while maintaining high inference efficiency via Grouped Query Attention (GQA) and quantization support (FP8, GPTQ, etc.).

Text131K context$0.14 / $0.57