Kimi K2.5 · deepinfra

Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.

Base modelAll models on this baseAll models of the providerto the provider

Read also: Kimi API pricing: Kimi K3.1 Pro, K3, K2.6 and K2.7 Code at every provider

All Moonshot Kimi models at every provider

Input, $/1M $0.45

Output, $/1M $2.25

Context 262 144

Max output 32 768

Accepts images, text, video

Last checked 04.11.2026 12:00:14 UTC

Source —