Developer platform
Build with Moo-AI.
Scale on your terms.
API access to Moozonian's general AI, fast overviews and coding models. Four straightforward monthly plans with controlled usage.
New to the Moo-AI API?Follow the API Wiki: authentication, integration examples, models and usage limits.
Explore API Wiki Starter
Monthly API subscription
$12 / month
500,000 Moo credits / month
Fast AI responses
Quick overview model family
Ideal for prototyping
10 RPM · 1 concurrent · 1,024 max output tokens
Choose Starter plan Developer
Monthly API subscription
$39 / month
2,000,000 Moo credits / month
Everything in Starter
Moo-AI Latest + standard coder
For websites and development tools
30 RPM · 2 concurrent · 2,048 max output tokens
Choose Developer plan Pro
Monthly API subscription
$99 / month
7,000,000 Moo credits / month
Everything in Developer
Coder v6, Web v6 and Coder Pro
Vision-model entitlement
60 RPM · 4 concurrent · 4,096 max output tokens
Choose Pro plan Business
Monthly API subscription
$299 / month
25,000,000 Moo credits / month
Everything in Pro
Higher concurrency and capacity
Cloud models require separate activation
120 RPM · 8 concurrent · 8,192 max output tokens
Choose Business plan Choose a plan to register or sign in. After email verification, you can review the recurring monthly charge securely in Stripe Checkout. Selecting a plan does not initiate a charge. Premium cloud models require separate activation.
OpenAI-compatible chat API
Use the standard chat-completions request format. Your key is secret and must be sent only from your backend.
curl -sS https://www.moozonian.com/moo-ai-api/v1/chat/completions \
-H "Authorization: Bearer YOUR_MOO_AI_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"moo-ai:latest","messages":[{"role":"user","content":"Hello from Moozonian"}],"max_tokens":256}'
GET /v1/models shows entitled models. GET /v1/usage shows used and available credits. POST /v1/chat/completions supports JSON and SSE streaming.
Model access by tier
Starter and above
moo-ai:quickoverview-fast
moo-ai:quickoverview
moo-ai:quickoveriew
qwen3:4b
llama3.2:3b
llama3.2:latest
moo-ai:quickoverview
moo-ai:quickoveriew
qwen3:4b
llama3.2:3b
llama3.2:latest
Developer and above
moo-ai:latest
qwen3:8b-q4_K_M
moo-ai:coder
qwen2.5-coder:7b-instruct-q4_K_M
qwen3:8b-q4_K_M
moo-ai:coder
qwen2.5-coder:7b-instruct-q4_K_M
Pro and above
moo-ai:coder-v6
moo-ai:coder-web
moo-ai:coder-web-v6
moo-ai:coder-pro
moo-ai:vision
moo-ai:coder-web
moo-ai:coder-web-v6
moo-ai:coder-pro
moo-ai:vision
Business and above
glm-5.3:cloud
mistral-large-4:cloud
mistral-large-4:cloud
Each response is metered as model weight × (input tokens + 3 × output tokens), with a separate allowance for vision images. Cloud models are off until commercial-use terms, upstream credentials, and cost controls are verified.