Kimi K2p5 moves to version kimi-k2.5

The OnAirToday AI Progress Tracker recorded a verified change to Moonshot's Kimi K2p5 (version kimi-k2.5): Version now kimi-k2.5 (was kimi-k2p5).

Kimi K2.5 is Moonshot AI’s open-weight multimodal model for text, image and video understanding, coding, and tool-using workflows. Published results distinguish standalone reasoning from tool-assisted and Agent Swarm configurations, which should not be treated as interchangeable.

What changed in this review:

• Uses the official Kimi K2.5 API identifier, kimi-k2.5.
• Adds the documented 256K-token context window.
• Adds documented USD pricing per million tokens: $0.60 uncached input and $3.00 output.
• Adds published AIME 2025, SWE-bench Verified, Humanity's Last Exam and Terminal-Bench results.
• Kimi K3 appears in Amazon Bedrock's September 18 announcement; this profile remains specific to K2.5.
• Adds the reported Kimi K3-assisted Redis exploit demonstration, explicitly distinguished from a K2.5 vulnerability.

Teams building on Kimi K2p5 should confirm limits, pricing and benchmark coverage against the vendor's own documentation before relying on these figures.

The full profile — capabilities, benchmark citations, known flaws and risk guidance — is on the tracker at /ai-models/kimi-k2p5.

References:

• https://huggingface.co/moonshotai/Kimi-K2.5
• https://github.com/MoonshotAI/Kimi-K2.5
• https://platform.moonshot.ai/docs/pricing/chat
• https://aws.amazon.com/blogs/machine-learning/introducing-kimi-k3-on-amazon-bedrock/