Overview
Welcome back!
Tokens Used
—
of — limit
API Calls
—
this month
Plan
—
current plan
Usage
0%
Token usage — last 30 days
Recent API Calls
| Model | Tokens | Latency | Time |
|---|---|---|---|
| No calls yet | |||
API Keys
Generate and manage your API keys. Keep them secret!
| Name | Key | Calls | Tokens | Last Used | Status | |
|---|---|---|---|---|---|---|
| No API keys yet | ||||||
Usage Analytics
Detailed breakdown of your API usage by model and time.
Total Tokens
—
Total Calls
—
Tokens Limit
—
Usage %
—
Daily token usage
By Model
| Model | Total Tokens | Total Calls |
|---|
Quick Start
Get your first API call running in 2 minutes.
1. Install the SDK
$ pip install openai # OpenAI SDK works with 3ai API
2. Make your first call
from openai import OpenAI
client = OpenAI(
api_key="your_3ai_sk_key",
base_url="http://43.205.211.64:8001/v1"
)
response = client.chat.completions.create(
model="3ai-llm-128k",
messages=[{"role":"user","content":"Hello!"}]
)
print(response.choices[0].message.content)
client = OpenAI(
api_key="your_3ai_sk_key",
base_url="http://43.205.211.64:8001/v1"
)
response = client.chat.completions.create(
model="3ai-llm-128k",
messages=[{"role":"user","content":"Hello!"}]
)
print(response.choices[0].message.content)
3. Available Models
| Model ID | Context | Best For | Status |
|---|---|---|---|
| 3ai-llm-128k | 128K | Enterprise, reasoning | Preview |
| 3ai-nano | 32K | Fast, edge | Preview |
| 3ai-embed | 8K | Embeddings | Coming Soon |
4. Rate Limits
| Plan | Tokens/month | Keys | RPM |
|---|---|---|---|
| Free | 1M | 2 | 10 |
| Pro | 10M | 10 | 60 |
| Enterprise | Unlimited | 50 | Unlimited |
API Playground
Test your API key and explore model responses.
Response will appear here...
Billing & Plan
Manage your subscription and usage limits.
Current Plan
Free
1M tokens/month
Pro Plan
₹999/mo
10M tokens/month
Enterprise
Custom
Unlimited + self-hosted