Access 26+ open-source AI models through a simple, OpenAI-compatible REST API. Free, no rate limits, self-hosted.
Get up and running in under a minute. Drop-in replacement for OpenAI's API.
curl https://openmind.theeverythingai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "qwen3:8b",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://openmind.theeverythingai.com/v1"
)
response = client.chat.completions.create(
model="qwen3:8b",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)
import OpenAI from 'openai';
const client = new OpenAI({
apiKey: 'YOUR_API_KEY',
baseURL: 'https://openmind.theeverythingai.com/v1',
});
const response = await client.chat.completions.create({
model: 'qwen3:8b',
messages: [
{ role: 'user', content: 'Hello!' }
],
});
console.log(response.choices[0].message.content);
26+ open-source models available. All running locally on our infrastructure.
| Model | Category | Size | Best For |
|---|---|---|---|
| qwen3:8b | Chat | 5.2 GB | General conversation, fast responses |
| gemma3:4b | Chat | 3.3 GB | Efficient, Google-quality responses |
| mistral:7b | Chat | 4.4 GB | Versatile, high-quality text |
| llama3.1:8b | Chat | 4.9 GB | Meta's most capable open model |
| deepseek-r1:8b | Reason | 5.2 GB | Complex reasoning, step-by-step |
| deepseek-r1:14b | Reason | 9.0 GB | Advanced reasoning tasks |
| qwq:32b | Reason | 19 GB | Deepest reasoning capability |
| qwen2.5-coder:7b | Code | 4.7 GB | Code generation & debugging |
| deepseek-coder:6.7b | Code | 3.8 GB | Specialized code tasks |
| devstral-small-2 | Code | 15 GB | Full-stack development |
| llava:7b | Vision | 4.7 GB | Image understanding & OCR |
| llama3.2-vision:11b | Vision | 7.8 GB | Advanced multimodal tasks |
| nomic-embed-text | 274 MB | Text embeddings for RAG | |
| dolphin3 | Special | 4.9 GB | Uncensored assistant |
| sqlcoder | Special | 4.1 GB | Natural language to SQL |
OpenAI-compatible endpoints. Use your existing OpenAI code — just change the base URL.
{
"model": "qwen3:8b",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Explain quantum computing"}
],
"temperature": 0.7,
"max_tokens": 2048,
"stream": false
}All API requests require a Bearer token in the Authorization header.
Include your API key in every request:Authorization: Bearer YOUR_API_KEY
Default: 60 requests/minute per API key. Contact admin for higher limits.
Every request is logged with model, tokens, and timestamp. View usage in the admin dashboard.
All endpoints use:https://openmind.theeverythingai.com/v1
Enter your name and email to get a free API key instantly. One key per email address.