hy3 API status on Kilo Code

Check provider

Available from Kilo Code

★★★★★★★★★★ 3.5 Benchmark-backed score

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Check providerOpenAI compatibleReasoningTool callingJSON modeTextReasoning

Check Provider Compare Save API Key

API Details

Copy-ready connection details

Use these values in your client or SDK.

Base URL

https://api.kilo.ai/api/gateway

Model ID

tencent/hy3

API format OpenAI-style

Technical Details

hy3 specifications

Provider and model catalog

Context window 262K

Max output 128K

Status Check provider

Family Hy

Released Jul 6, 2026

Last updated Oct 25, 2026

Free listing since Jul 6, 2026

Input text

Output text

Capabilities reasoning, tool calling, structured output, temperature control

Open weights Yes

Weights Hugging Face

External benchmark references

Benchmark	Score	Metric	Date
SWE-Bench Verified	78	resolved	Not listed
SWE-Bench Multilingual	75.8	score	Not listed
SWE-Bench Pro	57.9	score	Not listed
Terminal-Bench	71.7	score	Not listed

AI Recommendation

Should you use hy3?

hy3 is listed for chat workloads and supports a 262K context window.

Check Kilo Code's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.

Best for

Chat

Strengths & Weaknesses

Strengths

Long context window
Reasoning mode listed
Tool calling support
Structured JSON output

Watch outs

Current endpoint availability needs provider confirmation
Free-tier rate limits apply
Vision support is not listed

Benchmark Overview

Benchmark signals for hy3

Measured data

Intelligence General reasoning and instruction following

25.3/100

Coding Programming and code generation

58.8/100

Agentic Tool use and multi-step tasks

24.1/100

Speed Observed generation speed

84 tok/s

Context Maximum listed context window

262K

Pricing

hy3 pricing per 1M tokens

Check provider

Input $0.136 per 1M tokens

Output $0.555 per 1M tokens

Access Check provider Kilo Code

Rate limit 200 req/hr provider policy

Availability

hy3 availability by provider

Current provider only

We only found this hy3 listing on Kilo Code in the current catalog. Use the related models section for nearby alternatives.

Provider	Model listing	Access	Context	API	Limits
Kilo Code	tencent/hy3:free	Check provider	262K	OpenAI-style	200 req/hr

View Kilo Code setup guide →

Compare

hy3 alternatives to consider

Open comparison

Model	Provider	Context	Access
nvidia/nemotron-3-ultra-550b-a55b:free	Kilo Code	1.0M	Free tier
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free	Kilo Code	256K	Free tier
poolside/laguna-s-2.1:free	Kilo Code	262K	Free tier
cohere/north-mini-code:free	Kilo Code	256K	Free tier
nvidia/nemotron-3.5-lightning:free	Kilo Code	1.0M	Free tier

Typical Use Cases

hy3 use cases

Chat

hy3 is tagged for chat in this catalog and works with OpenAI-compatible client libraries.

FAQ

hy3 free API FAQ

Is hy3 free to use?

hy3 appears in the free model catalog for Kilo Code, but its current endpoint availability should be confirmed with the provider before use.

What is the hy3 model ID?

The model ID shown in this catalog is tencent/hy3.

What are the hy3 free tier rate limits on Kilo Code?

The listed free tier limit is 200 req/hr. Limits can change per account tier, so confirm against the provider dashboard.

What context window does hy3 support?

The listed context window is 262K tokens with up to 128K output tokens.

More about 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:...

For API keys, setup steps, and provider-level limits, see the Kilo Code provider page.