Moonshot AI

25 indexed models

25 matching models

MoonshotAI: Kimi K2 0905

moonshotai/kimi-k2-0905

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up t

Context window
262,144
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 15.3

Inference prices

moonshotai/Kimi-VL-A3B-Instruct

vertexAI/publishers/hf-moonshotai/models/kimi-vl-a3b-instruct@001

Input modalities
image, text
Output modalities
text
Capabilities
multimodal, visionInput

Benchmarks

  • MMBench: 98.9%

moonshotai/Kimi-VL-A3B-Thinking

vertexAI/publishers/hf-moonshotai/models/kimi-vl-a3b-thinking@001

Input modalities
image, text
Output modalities
text
Capabilities
multimodal, visionInput

Benchmarks

  • MMBench: 66.1%

moonshotai/Kimi-VL-A3B-Thinking-2506

vertexAI/publishers/hf-moonshotai/models/kimi-vl-a3b-thinking-2506@001

Input modalities
image, text
Output modalities
text
Capabilities
multimodal, visionInput

Benchmarks

  • MMBench: 98.7%

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace