Model Overview

kimi-k2.5

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.

text
Pricing
Input$ 0.45 /M
Output$ 2.20 /M

Public pricing comes from the currently exposed Xenodia model catalog and already reflects the minimum visible channel pricing.

Answer-first summary

Use this model when you need a public Xenodia surface with discoverable parameters, stable routing metadata, and documented request modes instead of provider-specific guesswork.

Recommended workflow: query /v1/models, inspect this model's capabilities, then call the relevant endpoint with only documented fields.

curl -s https://api.xenodia.xyz/v1/models

Capabilities

  • Brand: moonshotai
  • Upstream ID: moonshotai/kimi-k2.5
  • Async support: No
  • Request modes: sync
  • Reference input: Not supported

Supported parameters

No public parameter metadata has been published for this model yet.

Reference input rules

This model does not currently advertise public reference input support.

FAQ

What can kimi-k2.5 do on Xenodia?

kimi-k2.5 is exposed through Xenodia as a public model page with pricing, modalities, parameters, and documented request modes.

Does kimi-k2.5 support async tasks?

kimi-k2.5 does not currently advertise public task mode on Xenodia.