llm11

Hy-MT2-30B-A3B with Jev

Hy-MT2-30B-A3B is a model from Tencent, released 2026-08-20. It costs $0.074 per million input tokens and $0.295 per million output tokens, reads up to 8K tokens of context, and writes up to 4,096 tokens in one reply. Through llm11, set model to tencent/hy-mt2-30b-a3b.

Input price
$0.074 / 1M
Output price
$0.295 / 1M
Context window
8K tokens
Max output
4K tokens
Released
2026-08-20
Accepts
text

Read from the live catalogue and refreshed daily. At blended list price, 86% of the 332 priced models we can call cost more.

Using Hy-MT2-30B-A3B with Jev

Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Hy-MT2-30B-A3B does the answering when Jev sends it work, or when you name it yourself. At list price Hy-MT2-30B-A3B falls in the llm11-fast band, but no pack routes to it because its context window is under 32K tokens, the floor for pack members. You can still pin it: pass tencent/hy-mt2-30b-a3b as model and routing steps aside while verification still runs.

Jev is new, so we have not published results for Hy-MT2-30B-A3B with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.

About JevThe System One router

What a request costs

List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.

RequestTokens in / outOneA thousand
Short chat turn500 / 200$0.00010$0.096
Question over retrieved documents4,000 / 500$0.00044$0.444
Long document summary30,000 / 1,000$0.00251$2.51

Cheaper models to try

The catalogue has no benchmark score for Hy-MT2-30B-A3B, so this is a price ordering. It does not claim these answer as well.

Cheaper alternatives to Hy-MT2-30B-A3B
ModelInput / 1MOutput / 1MContext
Qwen Qwen2.5 7B Instruct$0.100$0.20033K
Qwen Qwen3 Coder 30B A3B Instruct$0.070$0.280262K
Qwen Qwen3.5-Flash$0.065$0.2601M
Qwen Qwen3.5-9B$0.100$0.150262K

Call it

Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.

python

from openai import OpenAI

client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")

res = client.chat.completions.create(
    model="tencent/hy-mt2-30b-a3b",
    messages=[{"role": "user", "content": "Hello"}],
)

More from Tencent

Other Tencent models
ModelInput / 1MOutput / 1MContext
Hy4 preview$0.834$2.501.05M
Hy-MT2-1.8B$0.044$0.1778K
Hy-MT2-7B$0.074$0.2958K
Hy3$0.132$0.528262K
Hy3 preview$0.180$0.600262K
Hunyuan A13B Instruct$0.140$0.570131K

All 7 Tencent models

Questions

What is Hy-MT2-30B-A3B with Jev?
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Hy-MT2-30B-A3B does the answering when Jev sends it work, or when you name it yourself. At list price Hy-MT2-30B-A3B falls in the llm11-fast band, but no pack routes to it because its context window is under 32K tokens, the floor for pack members. You can still pin it: pass tencent/hy-mt2-30b-a3b as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
Is Hy-MT2-30B-A3B a System One model?
No. Hy-MT2-30B-A3B answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
How much does Hy-MT2-30B-A3B cost?
$0.074 per million input tokens and $0.295 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00044, so a thousand of them is about $0.444. llm11 passes provider list price through and charges 5% when you buy credits.
What is the Hy-MT2-30B-A3B context window?
8,192 tokens, with up to 4,096 tokens in a single reply.
Does Hy-MT2-30B-A3B support tool calling and structured output?
The catalogue lists structured output, but it does not list tool calling and reasoning controls.
Can I use Hy-MT2-30B-A3B through llm11?
Yes. Set model to tencent/hy-mt2-30b-a3b on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
Does Jev route to Hy-MT2-30B-A3B?
Routing decisions are made by Jev, TypeSafe AI's System One model. At list price Hy-MT2-30B-A3B falls in the llm11-fast band, but no pack routes to it because its context window is under 32K tokens, the floor for pack members. You can still pin it: pass tencent/hy-mt2-30b-a3b as model and routing steps aside while verification still runs.
What is a cheaper alternative to Hy-MT2-30B-A3B?
Nearest in price and below it: Qwen Qwen2.5 7B Instruct at $0.100 in and $0.200 out, Qwen Qwen3 Coder 30B A3B Instruct at $0.070 in and $0.280 out and Qwen Qwen3.5-Flash at $0.065 in and $0.260 out. The catalogue has no benchmark score for Hy-MT2-30B-A3B, so this is a price ordering. It does not claim these answer as well.