KwaiKAT / kwaikat/kat-coder-pro-v2.5
KwaiKAT: KAT-Coder-Pro V2.5 - access through LLMTR
KAT-Coder-Pro V2.5 is Kwaipilot's (Kuaishou StreamLake) flagship agentic coding model. It is trained to carry out multi-step tasks inside real, executable repositories rather than to emit single-shot code, so it fits flows that browse a codebase, edit files, run tests, and chain tools. It reasons through a problem before answering (reasoning is always on), makes reliable tool/function calls, and accepts image input as base64 data URLs. It supports a 256K context window and prompt-cache reads.
Technical specifications
| Canonical ID | kwaikat/kat-coder-pro-v2.5 |
|---|---|
| Provider | KwaiKAT |
| Context window | 262,144 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text, image |
Pricing
A 6% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| CHAT_COMPLETIONS | INPUT_TEXT | PER_1M_TOKENS | $0.740000 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.150000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $2.96 |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions \
-H "Authorization: Bearer llmtr-your_key" \
-H "Content-Type: application/json" \
-d '{"model":"kwaikat/kat-coder-pro-v2.5","messages":[{"role":"user","content":"Hello"}]}'Related models
- KwaiKAT: KAT-Coder-Air V2.5 kwaikat/kat-coder-air-v2.5
- Gemma 4 llmtr/gemma-4
- Qwen 3.6 35B-A3B llmtr/qwen3-6-35b
- MedGemma 4B llmtr/medgemma-4b
- Trendyol 7B llmtr/trendyol-7b
- Magibu 11B v8 llmtr/magibu-11b-v8
- Sincap llmtr/sincap
- EmbeddingGemma 300M llmtr/embeddinggemma-300m