Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Support
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for moonshotai

MoonshotAI: Kimi VL A3B Thinking

moonshotai/kimi-vl-a3b-thinking

Model weights

Kimi-VL is a lightweight Mixture-of-Experts vision-language model that activates only 2.8B parameters per step while delivering strong performance on multimodal reasoning and long-context tasks. The Kimi-VL-A3B-Thinking variant, fine-tuned with chain-of-thought and reinforcement learning, excels in math and visual reasoning benchmarks like MathVision, MMMU, and MathVista, rivaling much larger models such as Qwen2.5-VL-7B and Gemma-3-12B. It supports 128K context and high-resolution input via its MoonViT encoder.

Modalities

Context

131K

Released

Apr 10, 2025

Knowledge Cutoff

Dec 2024

ActivityFAQ

Activity

Token volume and request traffic to this model over time.

About MoonshotAI: Kimi VL A3B Thinking

OpenRouter makes MoonshotAI: Kimi VL A3B Thinking available through a unified, OpenAI-compatible API using the model ID moonshotai/kimi-vl-a3b-thinking.

MoonshotAI: Kimi VL A3B Thinking accepts images and text and returns text. It has a 131,072-token context window.

It was released on April 10, 2025; its knowledge cutoff is December 31, 2024.

More models from MoonshotAI

  • Kimi K3
  • Kimi K2.7 Code
  • Kimi K2.6

Frequently asked questions

Kimi-VL is a lightweight Mixture-of-Experts vision-language model that activates only 2.8B parameters per step while delivering strong performance on multimodal reasoning and long-context tasks. The Kimi-VL-A3B-Thinking variant, fine-tuned with chain-of-thought and reinforcement learning, excels in math and visual reasoning benchmarks like MathVision, MMMU, and MathVista, rivaling much larger...

Kimi VL A3B Thinking has a 131,072 token context window.

Kimi VL A3B Thinking accepts images and text as input and returns text.

Kimi K3, Kimi K2.7 Code, Kimi K2.6 and 4 more are other text models from MoonshotAI.

Kimi VL A3B Thinking was released on April 10, 2025. Its knowledge cutoff is December 31, 2024.