Kimi-K2.6
Kimi-K2.6 (Moonshot AI) — 128K context, General tier. Input price $0.95/M · Output price $4/M · Avg latency 32ms. Routed via Routara OpenAI-compatible endpoint with multi-region failover and metered billing.
Input / 1M: $0.95/M · Output / 1M: $4/M · TTFT: 32ms
Specifications
- Developer: Moonshot AI
- Category: General
- Context window: 128K
- Input price: $0.95 / 1M
- Output price: $4 / 1M
- Avg latency: 32 ms
- SLA grade: A
Typical use cases
- Multilingual chatbots and customer support
- RAG pipelines with tool calling
- Code generation, review, and test synthesis
FAQ
- How is Kimi-K2.6 priced on Routara? — Input tokens are billed at $0.95/M and output at $4/M. Charges are metered per request with no separate platform fee.
- Is Kimi-K2.6 OpenAI-compatible? — Yes. Point any OpenAI SDK to https://api.routara.ai/v1 and set model to the Routara slug shown below.
- Does Kimi-K2.6 support streaming? — Streaming is supported when the upstream route is live. Use stream: true in chat.completions.
Related models
- mj_custom_zoom (/detail/mj-custom-zoom)
- mj_inpaint (/detail/mj-inpaint)
- multimodal-embedding-v1 (/detail/multimodal-embedding-v1)
Quick integration
- curl https://api.routara.ai/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"kimi/kimi-k2.6","messages":[{"role":"user","content":"Hello"}],"stream":true}'