Chutes

What is Chutes

Chutes is a serverless, decentralized AI compute platform for deploying, running, and scaling open-source AI models in production. It powers trillions of tokens per month and provides access to state-of-the-art open-source LLMs, image, video, speech, and music models. Built on Bittensor, Chutes offers high-performance inference, ephemeral jobs, batch processing, and TEE/secure compute.

How to use Chutes

1. Create an account on Chutes and obtain an API key.
2. Choose a model from the platform's library or deploy your own custom model.
3. Integrate via API using the OpenAI-compatible endpoint at https://llm.chutes.ai/v1/chat/completions.
4. Send requests with your API key and model name, optionally enabling streaming.
5. Scale automatically – Chutes handles infrastructure scaling based on demand.

Example Python code:

import os
import requests
 
payload = {
    "model": "moonshotai/Kimi-K2.6-TEE",
    "messages": [{"role": "user", "content": "Ship a concise launch checklist."}],
    "stream": True,
}
 
response = requests.post(
    "https://llm.chutes.ai/v1/chat/completions",
    headers={
        "Authorization": f"Bearer {os.environ['CHUTES_API_KEY']}",
        "Content-Type": "application/json",
    },
    json=payload,
    stream=True,
)
 
for line in response.iter_lines():
    if line and line.startswith(b"data: "):
        print(line.decode()[6:])

Features of Chutes

• Serverless AI Inference – Permanently hot models, stable and ready for scale.
• Multi-modality – Supports LLMs, image generation, video, speech, and music models.
• TEE/Secure Compute – Secure, private, and isolated compute environments.
• Decentralized Infrastructure – Open-source and built on Bittensor.
• Fast Model Availability – New SOTA open-source models available minutes after release.
• Flexible Deployment – Deploy any open model with just a few lines of code.
• Consumer Apps – Includes Chutes Chat and Chutes Search for end users.
• Embedding & Moderation Models – Embedding models for search/recommendation and content moderation tools.

Use Cases of Chutes

• AI-powered products – Integrate LLM inference into applications with automatic scaling.
• Batch processing – Run large-scale inference jobs efficiently.
• Ephemeral jobs – Execute short-lived AI tasks without managing infrastructure.
• Secure AI workloads – Use TEE compute for privacy-sensitive applications.
• Consumer AI tools – Power chatbots and search engines with Chutes Chat and Search.
• Custom model hosting – Deploy your own open-source models with minimal code.

Pricing

Chutes offers a Plus plan at $10 per month. Additional pricing details are available on the pricing page.

FAQ

What models are available on Chutes? Chutes provides a wide range of open-source models including LLMs (e.g., Kimi K2.6, GLM 5.2, Gemma 4 31B, DeepSeek, Qwen, Mistral), image generation, video, speech, and music models.

How do I get started? Sign up for an account, obtain an API key, and use the OpenAI-compatible API to start making requests.

Is Chutes decentralized? Yes, Chutes is built on Bittensor and uses decentralized, open-source infrastructure.

Can I deploy my own model? Yes, you can bring your own code and deploy any open model with just a few lines of code.

Does Chutes support secure compute? Yes, Chutes offers TEE (Trusted Execution Environment) for secure, private, and isolated compute.