Home/Models
Models/tencent

Hy3 preview

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.

tencent/hy3-preview
Organization
tencent
Family
Hy
Providers
5
Context
256,000
Output limit
64,000
Knowledge
—
Release
2026-04-20
Updated
—
Weights
Open
Input
text
Output
text
Capabilities
—

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

5 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
AIHubMix
hy3-preview
256,000128,000— / ————
View
Kilo Gateway
tencent/hy3-preview
262,144235,929— / ————
View
OpenCode
hy3-preview-free
256,00064,000— / ————
View
GMICloudvia OpenRouter
tencent/hy3-preview
bf16		262,144235,929$0.18 / $0.60YesYesNo
View
Tencent TokenHub
hy3-preview
256,00064,000— / ————
View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens
Input from$0.18Per 1M input tokens
Output from$0.60Per 1M output tokens
Available offers5Across 5 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 1 lowest-priced configuration
InputOutput
GMICloudgmicloud/bf16
$0.18$0.60
tencent/hy3-previewObserved
Input
$0.18
Output
$0.60
Cache read
$0.06
Hosting prices through OpenRouter All endpoints and cache rates
EndpointInput / 1MOutput / 1MCache read / 1MCache write / 1M
GMICloudgmicloud/bf16$0.18$0.60$0.06—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 1 endpoint
P50P75P90P99
GMICloudgmicloud/bf16
2,517–15,024.24 ms
All latency percentiles 1 endpoints
EndpointP50P75P90P99
GMICloudgmicloud/bf162,517 ms3,222 ms5,825.2 ms15,024.24 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 1 endpoint
P50P75P90P99
GMICloudgmicloud/bf16
78–148.36 t/s
All throughput percentiles 1 endpoints
EndpointP50P75P90P99
GMICloudgmicloud/bf1678 t/s89 t/s99 t/s148.36 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window
Availability by endpointCurrent overlapping windows · 1 endpoint
Endpoint5 minutes30 minutes24 hours
GMICloudgmicloud/bf16

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations
tencent/hy3-previewObserved
Benchmark profileArtificial Analysis · shared source scale from 0 to 60
Coding58.8
Agentic24.1
Intelligence25.3

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

EvaluationConfigurationSourceResultsDetails
Composite indicesHy3tencent/hy3-preview-20260421Artificial AnalysisIntelligence 25.3 · Coding 58.8 · Agentic 24.1
Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 24, 2026.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications
tencent/hy3-previewObserved
Context
262,144
Maximum output
235,929
Tokenizer
Other
Input
text
Output
text
Moderation
No
Added to OpenRouter
2026-04-22
Base URLhttps://openrouter.ai/api/v1
Model IDtencent/hy3-preview
Version IDtencent/hy3-preview-20260421
Weights IDtencent/Hy3-preview

Reasoning

Required
No
Enabled by default
Yes
Default effort
high
Supported efforts
high, low, none

Supported parameters

  • include_reasoning
  • max_tokens
  • reasoning
  • reasoning_effort
  • seed
  • temperature
  • tool_choice
  • tools
  • top_p

Default parameters

top p
1
temperature
0.9

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Hy3 preview cost?

Listed rates start at $0.18 per million input tokens and $0.60 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Hy3 preview?

There are 5 cataloged offers across 5 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 256,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Not reported. Structured output: Not reported. Support can vary by endpoint.

Resources

Hugging Face ↗
Catalog history · 3 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

  • · 53f900e530c6
  • · cd89873223ce
  • · fa75628a21d5