tencentCertifiedReleased 07/06/2026

Tencent Hy3

Tencent Hy3 is an open-source Mixture-of-Experts (MoE) large language model developed by Tencent's Hunyuan team. It has 295B total parameters, 21B active parameters, a 3.8B-parameter MTP layer, and a 256K context window. Hy3 is designed for agentic workflows, coding, reasoning, long-context understanding, tool-use scenarios, document analysis, and structured generation. The model improves on Hy3 Preview with stronger tool-call reliability, better output-format stability, improved long-context retention, and lower hallucination rates in Tencent's internal evaluations.

View API reference ↓
Input / output priceFrom$0.13 / $0.53per 1M
24h uptime100.00%
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "tencent/hy3",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
gmicloud262K262K1.9 s69 tps$0.14$0.58Read $0.035Write —5 featuresNoNoGlobalCertified
novita262K262K1.8 s115 tps$0.14$0.58Read $0.035Write —4 featuresNoNoGlobalCertified
tencent256K128K1.8 s63 tps$0.13$0.53Read $0.033Write —5 featuresNoNoGlobalCertified

Uptime

24 hours

Request success rate per provider.

gmicloud100.00%
novita100.00%
tencent100.00%

Throughput

last hour

P50 output tokens per second.

novita115 tps
gmicloud69 tps
tencent63 tps

Latency

last hour

P50 time to first token.

tencent1.8 s
novita1.8 s
gmicloud1.9 s

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "tencent/hy3",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Top-level parameters

Standard Chat Completions parameters work as documented. These have model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. tencent/hy3. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. Tencent Hy3 supports up to 262,144 output tokens.
reasoning{ effort: 'low' | 'medium' | 'high' }NoReasoning effort, mapped to the provider's native configuration. Reasoning tokens count toward output usage.
toolsTool[]NoFunction definitions the model can call. Tool calls are returned in choices[].message.tool_calls.
Supportedmax_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs

Input limits

InputSourcesLimits
Text—Prompt and response share the 262K-token context window

More models by tencent

ModelContextInputOutputCacheRelease
tencent/hy4-flash1.02M$0.035$0.14Read $0.0015Write —11/16/2026
tencent/hy41.02M$0.42$1.25Read $0.021Write —11/03/2026
tencent/hy4-preview1.02M$0.83$2.50Read $0.042Write —08/28/2026
tencent/hy-mt2-lite8K$0.044$0.18Read —Write —06/12/2026
tencent/hy-mt2-plus8K$0.074$0.30Read —Write —06/12/2026
tencent/hy-mt2-pro8K$0.074$0.30Read —Write —05/21/2026