Skip to content
ShilpBot
AI Models

Tencent Hy4: Pricing, Specs and Limits

Tencent Hy4: official release model with strong agentic gains over Hy4 Preview, 1M context, 0.42 in / 1.25 out per 1M tokens. Specs, limits and test prompts.

By ShilpBot Team · Published · 3 min read

Hy4 is the official release that follows Hy4 Preview. The listing says it delivers comprehensive improvements over the preview, particularly in agentic capabilities and long-horizon, real-world productivity tasks.

It accepts text and images, has a 1M-token context window, and is priced at about $0.42 per million input tokens and $1.25 per million output tokens.

Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.

Tencent Hy4 quick facts

DetailValue
DeveloperTencent
Model IDtencent/hy4
Added to the catalogue2026-11-04
TypeOfficial release model with strong agentic gains over Hy4 Preview
ParametersNot listed
Context windowabout 1M tokens (1,048,576)
Maximum output65,536 tokens
Input typestext, image
Price0.42 in / 1.25 out per 1M tokens (cached input 0.021)

Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Adjustable reasoning effort: listed.

What Tencent Hy4 is good for

  • Agentic workflows and long-horizon tasks, the focus of this release.
  • Image-plus-text tasks at moderate cost.
  • Long documents with a 1M-token window.

Limits of Tencent Hy4

  • Output is capped at 65,536 tokens, lower than several rivals.
  • If you tested Hy4 Preview, re-test, since behaviour changed.
  • No audio or video input.

How Tencent Hy4 compares

  • StepFun Step 5 Preview: It has a larger context window (1,048,576 against 1,000,000 tokens); its output cap is 65,536 tokens against 64,000; it does not accept video input; it costs 0.42 input and 1.25 output per million tokens against 1.00 and 2.70.
  • Nex AGI Nex-N2.6: It has a larger context window (1,048,576 against 262,144 tokens); its output cap is 65,536 tokens against 235,929; it costs 0.42 input and 1.25 output per million tokens against 0.12 and 0.40.
  • Mistral Large 4: Both have a 1,048,576-token context window; its output cap is 65,536 tokens against 262,144; it costs 0.42 input and 1.25 output per million tokens against 0.70 and 2.10.

Calling Tencent Hy4 from code

Use the model ID tencent/hy4 with any OpenAI-compatible client pointed at OpenRouter:

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "tencent/hy4", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'

Prompts that show what Tencent Hy4 can do

  1. Give it a multi-step office task such as drafting an email, a table and a summary from one set of notes.
  2. Upload a chart and ask for insights plus one limitation.
  3. Run a 20-step agent task and note where it loses track.

What Tencent Hy4 costs

The catalogue lists 0.42 per million input tokens and 1.25 per million output tokens, with cached input at 0.021 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 0.54. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $0.075 before caching. If your client reuses the same prompt prefix, cached input at 0.021 per million tokens can cut the input side of that bill by about 95 percent. Prices are set by the provider, can change, and may differ between hosting providers, so check the live model page before you budget.

Keep reading

Compare every paid model by price in our AI model pricing roundup, or see the free models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.

Frequently asked questions

How is Hy4 different from Hy4 Preview?

The listing says the official release brings broad improvements over the preview, with notable gains in agentic capability and long-horizon productivity tasks.

What are the cost and limits of Tencent Hy4?

As of 2026-11-16 the catalogue lists 0.42 per million input tokens and 1.25 per million output tokens. About 1M tokens (1,048,576) context window, up to 65,536 output tokens, model ID tencent/hy4. Prices can change, so check the live model page.

#Tencent Hy4#Tencent model#AI model pricing#AI API pricing#AI chat model#agentic model#OpenRouter