llm11

KAT-Coder-Pro V2.5 with Jev

KAT-Coder-Pro V2.5 is a model from Kwaipilot, released 2026-07-10. It costs $0.740 per million input tokens and $2.96 per million output tokens, reads up to 262K tokens of context, and writes up to 235,929 tokens in one reply. Through llm11, set model to kwaipilot/kat-coder-pro-v2.5.

Input price
$0.740 / 1M
Output price
$2.96 / 1M
Context window
262K tokens
Max output
236K tokens
Cached input
$0.150 / 1M

Read from the provider's prompt cache

Released
2026-07-10
Accepts
text

Read from the live catalogue and refreshed daily. At blended list price, 35% of the 332 priced models we can call cost more.

Using KAT-Coder-Pro V2.5 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. KAT-Coder-Pro V2.5 does the answering when Jev sends it work, or when you name it yourself. At list price KAT-Coder-Pro V2.5 falls in the llm11-balanced band, but no pack routes to it because Kwaipilot is not one of the labs the packs draw from. You can still pin it: pass kwaipilot/kat-coder-pro-v2.5 as model and routing steps aside while verification still runs.

Jev is new, so we have not published results for KAT-Coder-Pro V2.5 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$0.00096$0.962
Question over retrieved documents4,000 / 500$0.00444$4.44
Long document summary30,000 / 1,000$0.025$25.16

Cheaper models to try

The catalogue has no benchmark score for KAT-Coder-Pro V2.5, so this is a price ordering. It does not claim these answer as well.

Cheaper alternatives to KAT-Coder-Pro V2.5
ModelInput / 1MOutput / 1MContext
Qwen Qwen3.5 397B A17B$0.550$3.50262K
SpaceXAI Grok Build 0.1$1.00$2.00256K
DeepSeek DeepSeek V4 Pro 0423$0.936$1.871.05M
DeepSeek R1$0.700$2.5064K

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="kwaipilot/kat-coder-pro-v2.5",
    messages=[{"role": "user", "content": "Hello"}],
)

Questions

What is KAT-Coder-Pro V2.5 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. KAT-Coder-Pro V2.5 does the answering when Jev sends it work, or when you name it yourself. At list price KAT-Coder-Pro V2.5 falls in the llm11-balanced band, but no pack routes to it because Kwaipilot is not one of the labs the packs draw from. You can still pin it: pass kwaipilot/kat-coder-pro-v2.5 as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
Is KAT-Coder-Pro V2.5 a System One model?
No. KAT-Coder-Pro V2.5 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 KAT-Coder-Pro V2.5 cost?
$0.740 per million input tokens and $2.96 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00444, so a thousand of them is about $4.44. llm11 passes provider list price through and charges 5% when you buy credits.
What is the KAT-Coder-Pro V2.5 context window?
262,144 tokens, with up to 235,929 tokens in a single reply.
Does KAT-Coder-Pro V2.5 support tool calling and structured output?
The catalogue lists tool calling and structured output, but it does not list reasoning controls.
Can I use KAT-Coder-Pro V2.5 through llm11?
Yes. Set model to kwaipilot/kat-coder-pro-v2.5 on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
Does Jev route to KAT-Coder-Pro V2.5?
Routing decisions are made by Jev, TypeSafe AI's System One model. At list price KAT-Coder-Pro V2.5 falls in the llm11-balanced band, but no pack routes to it because Kwaipilot is not one of the labs the packs draw from. You can still pin it: pass kwaipilot/kat-coder-pro-v2.5 as model and routing steps aside while verification still runs.
What is a cheaper alternative to KAT-Coder-Pro V2.5?
Nearest in price and below it: Qwen Qwen3.5 397B A17B at $0.550 in and $3.50 out, SpaceXAI Grok Build 0.1 at $1.00 in and $2.00 out and DeepSeek DeepSeek V4 Pro 0423 at $0.936 in and $1.87 out. The catalogue has no benchmark score for KAT-Coder-Pro V2.5, so this is a price ordering. It does not claim these answer as well.