Kimi K2.5on Krater.ai
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
Released January 27, 2026
Specifications
Kimi K2.5 at a glance
Context
262.1K tokens
Max output
262.1K tokens
Input
Text, Image
Output
Text
Input price
$0.57 / 1M
Output price
$2.85 / 1M
Capabilities
What it is good at
Catalog capabilities
- Accepts image input
- Generates text responses
- Supports tool calling
- Supports structured outputs
Good for
Benchmarks
Catalog data, not Krater benchmarks.
Coding index score
46.8
Agentic index score
21.7
Intelligence index score
35.4
Design Arena godotgamedev rank
#9
Design Arena fullstack rank
#18
Compare
Compare Kimi K2.5
Kimi K2.5 vs Kimi K2.6
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration.
Open comparisonKimi K2.5 vs Kimi K2.7 Code
Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts.
Open comparisonKimi K2.5 vs Kimi K3
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
Open comparisonFAQ
Questions about Kimi K2.5
Clear answers based on the model catalog and Krater access.
Use Kimi K2.5 in your API
Connect with Krater's unified API.