Kimi K2.5: 1T Agentic MoE Inference on Modular

Kimi K2.5 by Moonshot AI is a ~1T MoE model with 32B active parameters, supporting text and vision with reasoning capabilities.

Deploy dedicated endpoint

Try in Playground

Example Usage

Input

Python


  from openai import OpenAI
  
  client = OpenAI(
      base_url="https://model.api.modular.com",
      api_key="<your_api_token>",
  )
  
  response = client.chat.completions.create(
      model="moonshotai/Kimi-K2.5",
      messages=[
          {"role": "system", "content": "You are a helpful assistant."},
          {"role": "user", "content": "Explain speculative decoding in 3 sentences."},
      ],
      stream=True,
  )
  
  for chunk in response:
      if chunk.choices[0].delta.content:
          print(chunk.choices[0].delta.content, end="")

Get your API token

Output

  Speculative decoding uses a smaller draft model to predict multiple
  tokens ahead, then verifies them against the full model in a single
  pass. Accepted tokens skip individual generation steps, improving
  throughput without sacrificing accuracy. It's most effective when the
  draft model closely matches the target model's distribution.

Input

Cute orange cartoon fox with a small brown backpack sitting on grass in a bright, colorful forest.

Output

  “The image shows a fox wearing a backpack in a forest.”

Model Details

Developed by
Moonshot AI
Model family
moonshotai/Kimi-K2.5
Modality
LLM,
Vision,
Context Window
256K
Total Params
~1T
Precision
BF16 / INT4
Deployment options
Shared, Dedicated, Self-hosted

Why choose Kimi K2.5 on Modular?

High performance, out of the box
Run leading open models with strong default performance and the ability to optimize down to the kernel — extracting more from every GPU.
Lower Infrastructure Costs
Deploy efficiently across NVIDIA and AMD hardware to reduce GPU count, increase throughput, and avoid expensive closed-model licensing.
Easy Integration
Integrate through an OpenAI-compatible endpoint, swap models freely, and scale across clouds or hardware without redesigning your application stack.

Want to self-host this model with our open source infrastructure?

Read How

🔥 Trending models

DeepSeek V3.2

DeepSeek V3.2 is a 685B MoE model with 37B active parameters, excelling at code, math, and general reasoning tasks.

LLM

FLUX.2 Klein 9B

FLUX.2 [klein] 9B is a 9 billion parameter rectified flow transformer capable of generating images from text descriptions and supports multi-reference editing capabilities.

Image

GLM-5

GLM-5 by Zhipu AI is a 744B MoE model with 44B active parameters, featuring strong reasoning capabilities across multilingual tasks.

LLM

MiniMax M2.5

MiniMax M2.5 is a 230B MoE model with 10B active parameters, optimized for efficient text generation.

LLM

Similar models

Ministral 14B

Ministral 14B by Mistral AI is a dense 14B parameter model supporting text and vision with reasoning.

LLM

Vision

MiniMax M2.5

MiniMax M2.5 is a 230B MoE model with 10B active parameters, optimized for efficient text generation.

LLM

DeepSeek V3.1

LLM

DeepSeek R1 Distill Llama 70B

DeepSeek R1 Distill Llama 70B is a dense 70B parameter distilled reasoning model.

LLM

View all models

Get started with Modular

Request a demo
Schedule a demo of Modular and explore a custom end-to-end deployment built around your models, hardware, and performance goals.
- Distributed, large-scale online inference endpoints
- Highest-performance to maximize ROI and latency
- Deploy in Modular cloud or your cloud
- View all features with a custom demo
Book a demo
Talk with our sales lead Jay!
30min demo. Evaluate with your workloads. Ask us anything.

Talk to us!
Book a demo for a personalized walkthrough of Modular in your environment. Learn how teams use it to simplify systems and tune performance at scale.
- Custom 30 min walkthrough of our platform
- Cover specific model or deployment needs
- Flexible pricing to fit your specific needs
Book a demo
Talk with our sales lead Jay!
Start using MAX
( FREE )
Run any open source model in 5 minutes, then benchmark it. Scale it to millions yourself (for free!).
Install MAX
What is MAX?
Start using Mojo
( FREE )
Install Mojo and get up and running in minutes. A simple install, familiar tooling, and clear docs make it easy to start writing code immediately.
Install Mojo🔥
What is Mojo🔥?