Hy3
About this model
Hy3 is an AI model from Tencent, made available through the API on July 6, 2026. It can read up to 262,144 tokens in one request, roughly 492 pages of text, and write up to 128,000 tokens in a single answer.
Through the API it costs $0.13 per million input tokens and $0.53 per million output tokens. Its pricing puts it among the more affordable models we track, which makes it a good fit for high-volume tasks.
It supports extended reasoning: it can "think" step by step before answering, which helps on maths, code and complex questions. It can call tools and functions, so developers can connect it to search, databases or other software. Its weights are openly published (tencent/Hy3), so it can also be downloaded and run on your own hardware.
Quality scores
Rankings →Not rated yet. Independent test results usually appear a few weeks after a model is released.
Where to use it
Companies that serve this model through an API: 6. Prices per million tokens, cheapest first.
| Provider | Inputi | Outputi | Contexti | Uptime (24 h)i |
|---|---|---|---|---|
DeepInfraCheapestfp4 | $0.13 | $0.53 | 256K | 99.5% |
TencentOfficialCheapestfp8 | $0.13 | $0.53 | 256K | 99.9% |
Novita | $0.14 | $0.58 | 256K | 99.7% |
GMICloudbf16 | $0.14 | $0.58 | 256K | 99.9% |
Phala | $0.15 | $0.64 | 256K | 99.9% |
AtlasCloudfp8 | $0.20 | $0.80 | 256K | 100.0% |
Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.
Use it in your code
Call Hy3 through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "tencent/hy3", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'import os
from openai import OpenAI
client = OpenAI(base_url="https://openrouter.ai/api/v1", api_key=os.environ["OPENROUTER_API_KEY"])
reply = client.chat.completions.create(
model="tencent/hy3",
messages=[{"role": "user", "content": "Hello! What can you do?"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://openrouter.ai/api/v1", apiKey: process.env.OPENROUTER_API_KEY });
const reply = await client.chat.completions.create({
model: "tencent/hy3",
messages: [{ role: "user", content: "Hello! What can you do?" }],
});
console.log(reply.choices[0].message.content);The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.
What it costs in practice
- 1,000 chat replies$0.224
- Summarise a 100-page document$0.0071
- An app with 10,000 requests a day for a month$103
Similar-priced alternatives
| Model | Inputi | Outputi | Contexti | |
|---|---|---|---|---|
MiMo-V2.6-FlashXiaomi | $0.14 | $0.28 | 1M | Compare with ⇄ |
Perceptron Mk1.5Perceptron | $0.15 | $1.50 | 36K | Compare with ⇄ |
Qwen3.8 Omni FlashAlibaba Qwen | $0.15 | $0.47 | 1M | Compare with ⇄ |
GLM 5.3 FlashZ.ai (Zhipu) | $0.15 | $0.50 | 1M | Compare with ⇄ |
GPT-6 Luna ProOpenAI | $0.10 | $0.50 | 1.1M | Compare with ⇄ |
| $0.10 | $0.20 | 1M | Compare with ⇄ |
Frequently asked questions
- How much does Hy3 cost?
- Hy3 costs $0.13 per million input tokens and $0.53 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $0.224.
- What is the context window of Hy3?
- Hy3 can read up to 262,144 tokens in one request, about 492 pages of text. It can write up to 128,000 tokens in a single answer.
- Is Hy3 open source?
- Yes. Its weights are published (tencent/Hy3), so you can download it and run it on your own hardware, or use it through one of 6 API providers.
- Who makes Hy3?
- Hy3 is made by Tencent. It became available through the API on July 6, 2026.
- Can Hy3 read images?
- No. Hy3 only accepts text as input.
- What are the alternatives to Hy3?
- Models with a similar price from other companies include MiMo-V2.6-Flash, Perceptron Mk1.5 and Qwen3.8 Omni Flash. You can compare them side by side on this page.