tencentNot yet certifiedReleased 11/03/2026

Tencent Hy4

Tencent Hy4 is a text model for coding, reasoning, and agentic workflows. It supports tool calling, structured outputs, and prompt caching, with a 1M-token context window for tasks such as software engineering, document analysis, and office automation.

View API reference ↓
Input / output priceFrom$0.42 / $1.25per 1M
24h uptime100.00%

Listed for reference. Inference Bureau dispatches only to certified routes, so requests for this model are refused until one is certified. See certified models.

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/hy4",
  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
tencent1.02M64K1.6 s85 tps$0.42$1.25Read $0.021Write —6 featuresNoNoGlobalListed

Uptime

24 hours

Request success rate per provider.

tencent100.00%

Throughput

last hour

P50 output tokens per second.

tencent85 tps

Latency

last hour

P50 time to first token.

tencent1.6 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/hy4",
  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/hy4. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. Tencent Hy4 supports up to 64,000 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 1.02M-token context window
ImageURL, base64Sent as image_url content parts; counts as input tokens

More models by tencent

ModelContextInputOutputCacheRelease
tencent/hy4-flash1.02M$0.035$0.14Read $0.0015Write —11/16/2026
tencent/hy4-preview1.02M$0.83$2.50Read $0.042Write —08/28/2026
tencent/hy3262K$0.14$0.58Read $0.035Write —07/06/2026
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