by Moonshot AI

Kimi K2.5.

multimodal open weights 262K ctx

Kimi K2.5 is Moonshot AI's flagship agentic model and a new SOTA open model. It unifies vision and text, thinking and non-thinking modes, and single-agent and multi-agent execution into one model. Fireworks enables users

Where to use it

Cheapest hosted endpoints.

Provider	Access	$/M in	$/M out
Moonshot AI Platform	api direct	—	—	Launch ↗
Fireworks AI	hosted inference	—	—	Launch ↗

FAQ

Frequently asked.

How do I run Kimi K2.5?

Kimi K2.5 is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.

Where can I access Kimi K2.5?

Kimi K2.5 is available via Moonshot AI Platform, Fireworks AI. Each access option lists its own pricing (per million tokens or hourly hosting).

How much does it cost to run Kimi K2.5?

Self-hosting cost depends on the GPU you rent and the throughput you need. See the Run It Yourself tab for GPU configurations and hourly cost estimates.

Is Kimi K2.5 open-source or proprietary?

Kimi K2.5 is open-weight under the license. You can download and self-host it.