Features How It Works API Playground Models Benefits FAQ

Intelligence Without Gatekeepers

Free AI inference with OpenAI-compatible endpoints. No API keys to buy. No accounts to create. Connect a wallet, get a key, start building.

View Source
8
AI Models
100%
Free
OpenAI
Compatible
Phase 3
Decentralized

Built for Developers

Everything you need to run AI inference without intermediaries.

Zero-Cost Inference

No pay-per-token billing. No subscription fees. The network is sustained by contributors, not your wallet.

Drop-In Compatible

Works with any OpenAI-compatible client. Just change the base URL. No SDK changes needed.

Drop-In API

OpenAI-compatible endpoints. Switch from any provider with a one-line base URL change.

Encrypted In Transit

All requests use HTTPS encryption. Your prompts and responses are protected in transit.

Fast Responses

Optimized inference pipeline with streaming support. Token-by-token delivery starts immediately.

Open Source

Every line of code is auditable. Fork it. Run your own network. Contribute back. It's all on GitHub.

Four Steps to Free Inference

From prompt to response in seconds, with zero cost.

1

Send Prompt

Submit your request through the OpenAI-compatible API with your unique key.

2

Authenticate

Your gb_ API key is validated to ensure authorized access to the inference API.

3

Inference

The selected model processes your prompt and generates a response using optimized inference.

4

Stream Response

Output is streamed token-by-token back to your client via the OpenAI-compatible API.

Get Your Free API Key

Connect a wallet to generate a deterministic API key. No sign-up forms, no emails.

Connect Your Wallet

Choose a wallet to generate your unique API key.

Connected:
API Key:
Active Model
mimo-v2.5-pro
70B params · General Purpose · Meta
READY

Select a Model

mimo-v2.5-pro
Flagship
mimo-v2.5
General
mimo-v2-flash
Fast
mimo-v2-omni
Multimodal

Quick Commands

curl -X POST https://api.xiaomimimo.com/v1/chat/completions ...
export MIMO_API_KEY=your_key
export MIMO_BASE_URL=https://api.xiaomimimo.com/v1

Integration Examples

import requests

response = requests.post(
    "https://api.xiaomimimo.com/v1/chat/completions",
    headers={
        "Authorization": "Bearer YOUR_MIMO_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model": "mimo-v2.5-pro",
        "messages": [{"role": "user", "content": "Hello!"}]
    }
)
print(response.json()["choices"][0]["message"]["content"])
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_MIMO_API_KEY",
    base_url="https://api.xiaomimimo.com/v1"
)

response = client.chat.completions.create(
    model="mimo-v2.5-pro",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    api_key="YOUR_MIMO_API_KEY",
    base_url="https://api.xiaomimimo.com/v1",
    model="mimo-v2.5-pro"
)

result = llm.invoke("Hello!")
print(result.content)
curl -X POST https://api.xiaomimimo.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_MIMO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mimo-v2.5-pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
const response = await fetch("https://api.xiaomimimo.com/v1/chat/completions", {
    method: "POST",
    headers: {
        "Authorization": "Bearer YOUR_MIMO_API_KEY",
        "Content-Type": "application/json"
    },
    body: JSON.stringify({
        model: "mimo-v2.5-pro",
        messages: [{ role: "user", content: "Hello!" }]
    })
});
const data = await response.json();
console.log(data.choices[0].message.content);
# In your hermes-agent config (config.yaml):
providers:
  mimo:
    type: openai
    api_key: YOUR_MIMO_API_KEY
    base_url: https://api.xiaomimimo.com/v1
    model: mimo-v2.5-pro

# Or via environment variables:
export HERMES_PROVIDER=openai
export OPENAI_API_KEY=YOUR_MIMO_API_KEY
export OPENAI_BASE_URL=https://api.xiaomimimo.com/v1

Quick Start

1
Connect your wallet above to generate a free API key.
2
Copy your API key and set it as an environment variable.
3
Choose a model from the grid above and note its name.
4
Make your first request using any of the code examples below.
A

Install the SDK

Use pip install openai or npm install openai to get started with the official SDK.

B

Set Your Key

Export GITBLOCK_API_KEY as an environment variable or pass it directly to the client.

C

Point to GitBlock

Set the base URL to https://api.xiaomimimo.com/v1 — that's the only change from OpenAI.

D

Start Building

Send chat completions, embeddings, and more. Full OpenAI API compatibility.

Available Models

Curated models optimized for different tasks. All accessible through a single API endpoint.

Flagship

mimo-v2.5-pro

Xiaomi MiMo

Xiaomi's most capable reasoning model. Top-tier performance on math, code, and complex logic tasks.

General

mimo-v2.5

Xiaomi MiMo

General-purpose MiMo model. Strong balance of speed and reasoning for everyday AI tasks.

Fast

mimo-v2-flash

Xiaomi MiMo

Optimized for speed and efficiency. Ideal for latency-sensitive applications and high-throughput workloads.

Multimodal

mimo-v2-omni

Xiaomi MiMo

Multimodal model supporting text and vision. Send images alongside text for visual understanding tasks.

Why GitBlock?

The advantages of a truly open inference network.

Truly Zero Cost

No hidden fees, no rate limits behind paywalls. The network runs on community-contributed compute.

Privacy First

All requests use HTTPS encryption. No prompts are stored or used for training.

Always Online

Reliable hosted infrastructure with automatic failover. Designed for consistent availability.

Works Anywhere

No geographic restrictions. Access the network from any country, any device, any time.

Roadmap: Distributed

Phase 3 will add a decentralized node network. Community members will contribute GPU compute for shared access.

Fork & Build

The entire codebase is open. Fork it, customize it, run your own private network.

Frequently Asked Questions

Everything you need to know about GitBlock.

There's no catch. GitBlock is a community-driven project sustained by the team. Free access is a core principle — the goal is to make AI inference available to everyone. We plan to support community compute contributions in Phase 3.
All traffic is encrypted via HTTPS. Your prompts are not stored, logged, or used for training. We take privacy seriously and minimize data retention.
Your wallet address is used to deterministically generate your API key. This means no sign-up forms, no email collection, and no central database of users. Your key is derived from your address and can be regenerated anytime.
Currently 8 models are available including Llama 3.3, DeepSeek Coder, Qwen 2.5, Mistral, CodeLlama, Phi-3, Gemma 4, and Yi 1.5. We plan to expand the catalog as the project grows.
Not yet — but it's coming. Phase 3 of our roadmap includes a decentralized node network where anyone can contribute GPU compute. Join our GitHub to stay updated on development progress.
GitBlock uses the exact same API format as OpenAI. The only difference is the base URL — just point your client to api.xiaomimimo.com. The key difference: it's completely free.
There are soft limits to prevent abuse (currently 20 requests per minute per key). If you need higher throughput, open an issue on GitHub and we'll work with you.