Moonshotai Kimi K2 Instruct

kimi-k2-instruct (custom) — 128K context, General tier. Input price: $0.57/M · Output price: $2.3/M · Avg latency 32ms. Routed via Routara OpenAI-compatible endpoint with multi-region failover and metered billing.

Live gateway pricing · routed to the best upstream for your region

Specifications

  • Developer: custom
  • Category: General
  • Context window: 128K
  • Input price: $0.57 / 1M
  • Output price: $2.3 / 1M
  • Avg latency: 32 ms
  • SLA grade: B

Typical use cases

  • Multilingual chatbots and customer support
  • RAG pipelines with tool calling
  • Code generation, review, and test synthesis

FAQ

  • How is kimi-k2-instruct priced on Routara? — Input tokens are billed at $0.57/M and output at $2.3/M. Charges are metered per request with no separate platform fee.
  • Is kimi-k2-instruct 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-instruct support streaming? — Streaming is supported when the upstream route is live. Use stream: true in chat.completions.

Related models

  • multimodal-embedding-v1 (/detail/multimodal-embedding-v1)
  • qwen-image-max (/detail/qwen-image-max)
  • audio1.0 (/detail/audio1-0)

Quick integration

  • curl https://api.routara.ai/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"moonshotai/kimi-k2-instruct","messages":[{"role":"user","content":"Hello"}],"stream":true}'