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
- Released
- 2026-07-10
- Accepts
- text
Read from the provider's prompt cache
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.
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.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00096 | $0.962 |
| Question over retrieved documents | 4,000 / 500 | $0.00444 | $4.44 |
| Long document summary | 30,000 / 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.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Qwen Qwen3.5 397B A17B | $0.550 | $3.50 | 262K | |
| SpaceXAI Grok Build 0.1 | $1.00 | $2.00 | 256K | |
| DeepSeek DeepSeek V4 Pro 0423 | $0.936 | $1.87 | 1.05M | |
| DeepSeek R1 | $0.700 | $2.50 | 64K |
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.