Models / Tencent

Hunyuan A13B Instruct API pricing

$0.56 in, $2.28 out per million tokens.

hunyuan-a13b-instructmanaged routeOpenAI SDK

Price · per million tokens, USD

Get a key
TokensTencent list priceUplinkSwitchSaving
Input—$0.56—
Cached inputBilled at the input rate.
Output—$2.28—
No list price on record. Same price on every host.

Hunyuan A13B Instruct: what it is · from Tencent’s own model card, read 2026-10-20

Tencent’s Hunyuan-A13B, a fine-grained mixture of experts built for efficient reasoning and general use. It runs on fewer resources than its size suggests. It is served as hunyuan-a13b-instruct at $0.56 input and $2.28 output per million tokens, on the same key as every other model in the catalog.

Hunyuan A13B Instruct
DeveloperTencent
Parameters80B total, 13B active per token
Context256K tokens natively
Licensethe Tencent Hunyuan A13B license
Published2025-06-25
Downloads, 30 days to 2026-10-2071,166
Sourcetencent/Hunyuan-A13B-Instruct

From tencent/Hunyuan-A13B-Instruct, read 2026-10-20.

curl
curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "authorization: Bearer sk-uplink-live-..." \
  -H "content-type: application/json" \
  -d '{"model":"hunyuan-a13b-instruct","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'

Hunyuan A13B Instruct next to Tencent’s other models · per million tokens, live

ModelHere, in / out1,000 chat turns
Hy3$0.165 / $0.66$0.66
Hy4 preview$0.2502 / $0.75$0.88
Hunyuan A13B Instruct$0.56 / $2.28$2.26
Hy3 Uncensored$0.75 / $4.00$3.50

A chat turn is 2,000 input and 500 output tokens. Live from the catalog, ordered by the cost of 1,000 turns.

Worked for Hunyuan A13B Instruct: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $0.56 input and $2.28 output per million tokens, that is $1.12 + $1.14 = $2.26, paid from prepaid credit with no subscription.

Hunyuan A13B Instruct 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="hunyuan-a13b-instruct",
    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: 'hunyuan-a13b-instruct',
  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":"hunyuan-a13b-instruct","messages":[{"role":"user","content":"Hello"}]}'

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

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.

Hunyuan A13B Instruct questions

What is Hunyuan A13B Instruct?
Hunyuan A13B Instruct is a model from Tencent. Through UplinkSwitch it answers the OpenAI SDK on one key as hunyuan-a13b-instruct.
How much does the Hunyuan A13B Instruct API cost?
$0.56 per million input tokens and $2.28 per million output tokens.
Is Hunyuan A13B Instruct 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 $0.0017.
What is the Hunyuan A13B Instruct model id?
hunyuan-a13b-instruct. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.
How do I get a Hunyuan A13B Instruct API key?
Create one in the console at uplinkswitch.ai/console: prepaid credit from $10, no subscription, and the key is live at once. The same key calls Hunyuan A13B Instruct and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.
Is it the real Hunyuan A13B Instruct?
Every day each model gets the same test prompt, and a model always counts that prompt the same way; a swapped one would not. Hunyuan A13B Instruct's latest result: Same fingerprint since Oct 20, no answer since Oct 22.
Is there a Hunyuan A13B Instruct API?
Yes: hunyuan-a13b-instruct on the OpenAI format at https://api.uplinkswitch.com/v1, $0.56 input and $2.28 output per million tokens. No weights to download and no GPU of your own; the key also runs every other model in the catalog.
How many parameters does Hunyuan A13B Instruct have?
80B total, 13B active per token, per tencent/Hunyuan-A13B-Instruct.
What is Hunyuan A13B Instruct's context window?
256K tokens natively, per tencent/Hunyuan-A13B-Instruct.
Is Hunyuan A13B Instruct open source?
Its weights are open on Hugging Face (tencent/Hunyuan-A13B-Instruct); the license is the Tencent Hunyuan A13B license.
What does Hunyuan A13B Instruct cost per 100 messages?
$0.226 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.56 input and $2.28 output per million tokens, from prepaid credit with no subscription.