How much does the Hy3 API cost?

$0.0417 per million input tokens and $0.1668 per million output tokens. Tencent's list price is $0.139 and $0.556, so this is 70% under Tencent's list price.

It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.0001.

What is the Hy3 context window?

Hy3 has a 262,144-token context window, with up to 131,072 output tokens per request. It takes text input.

What is the Hy3 model id?

hy3. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.

Every day each model gets the same test prompt, and a model always counts that prompt the same way; a swapped one would not. Hy3's latest result: Same fingerprint since Oct 19.

UplinkSwitch

Models / Tencent

Hy3 API pricing

$0.0417 in, $0.1668 out per million tokens, 70% under Tencent's list price.

hy3managed routeOpenAI SDK

Price · per million tokens, USD

Tokens	Tencent list price	UplinkSwitch	Saving
Input	$0.139	$0.0417	-70%
Cached input	Billed at the input rate.
Output	$0.556	$0.1668	-70%

List price: Tencent's published rate, read October 2026. Same price on every host.

Real-model check: Same fingerprint since Oct 19

Hy3 specs

Context window: 262,144 tokens
Max output: 131,072 tokens
Input: text
Released: July 6, 2026

Hy3 API · base URL and key

Python · OpenAI SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uplinkswitch.com/v1",
    api_key="sk-uplink-live-...",
)

completion = client.chat.completions.create(
    model="hy3",
    messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)

TypeScript · OpenAI SDK

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.uplinkswitch.com/v1',
  apiKey: 'sk-uplink-live-...',
});

const completion = await client.chat.completions.create({
  model: 'hy3',
  messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);

curl

curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "authorization: Bearer sk-uplink-live-..." \
  -H "content-type: application/json" \
  -d '{"model":"hy3","messages":[{"role":"user","content":"Hello"}]}'

Guides: Cursor, Cline, Roo Code, Kilo Code, SDKs.

What would it cost? · paste a prompt, priced before you send it

Prompt

Answer length, tokens

Input is counted at about 4 characters per token.

Cheapest first. A real request is billed on the provider's own token count. Same estimate as JSON: POST https://api.uplinkswitch.com/v1/estimate, no key needed.

Hy3 questions

How much does the Hy3 API cost?: $0.0417 per million input tokens and $0.1668 per million output tokens. Tencent's list price is $0.139 and $0.556, so this is 70% under Tencent's list price.
Is Hy3 free?: It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.0001.
What is the Hy3 context window?: Hy3 has a 262,144-token context window, with up to 131,072 output tokens per request. It takes text input.
What is the Hy3 model id?: hy3. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
Is it the real Hy3?: Every day each model gets the same test prompt, and a model always counts that prompt the same way; a swapped one would not. Hy3's latest result: Same fingerprint since Oct 19.

Get a key · All models