Developer Platform

Built for Developers, Loved by Engineers

Everything you need to integrate, build, and scale AI — clean APIs, great docs, SDKs for every language, and a thriving developer community.

Get Free API KeyView API Docs
< 1s
Avg Response Time
99.9%
API Uptime
7
Official SDKs
$0
To Get Started

Quickstart

Get a streaming response in 60 seconds

pythonCopy
from mentneo import Mentneo

client = Mentneo(api_key="...")

response = client.chat.complete(
    model="mentneo-pro",
    messages=[{"role": "user", "content": "Hello"}],
    stream=True,
)

for chunk in response:
    print(chunk.choices[0].delta.content, end="")
typescriptCopy
import Mentneo from '@mentneo/sdk';

const client = new Mentneo({ apiKey: process.env.MENTNEO_API_KEY });

const stream = await client.chat.complete({
  model: 'mentneo-pro',
  messages: [{ role: 'user', content: 'Hello' }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}
curlCopy
curl https://api.mentneo.com/v1/chat/completions \
  -H "Authorization: Bearer $MENTNEO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mentneo-pro",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'

Developer FAQ

Sign up at mentneo.com/signup to get a free API key instantly — no credit card required. Free tier includes 10,000 tokens per day. Paid plans start at $0.001 per 1K tokens.

Yes. Mentneo APIs are fully compatible with the OpenAI Python and TypeScript SDKs. Simply change the base_url to api.mentneo.com and your existing OpenAI integration will work without any other code changes.

Mentneo provides official SDKs for Python, TypeScript/JavaScript, Java, Go, Rust, Ruby, and PHP. For other languages, you can use our REST API directly — any HTTP client will work.

Yes. All Mentneo APIs support server-sent event (SSE) streaming for real-time token delivery. Enable streaming with stream=True (Python) or stream: true (TypeScript).

Free tier allows 10,000 tokens/day, 60 requests/minute, and 3 concurrent requests. Paid plans have significantly higher limits and can be customized for enterprise usage patterns.