Getting Started with VoltAI API
Welcome to VoltAI API documentation. Get started with our powerful AI models in minutes.
Quick Start
- Join our Discord server to get your API key
- Use the
/generate
command in Discord - Start making requests to our API endpoints
https://api.voltapi.online/v1
Authentication
All API requests require authentication using an API key.
Getting Your API Key
To obtain your API key:
- Join our Discord server
- Navigate to the appropriate channel
- Use the
/generate
command - Your unique API key will be generated and sent to you
Authorization: Bearer YOUR_API_KEY
API Endpoints
VoltAI provides the following endpoints for interacting with our AI models.
List all available models
curl https://api.voltapi.online/v1/models \
-H "Authorization: Bearer YOUR_API_KEY"
Create a chat completion
curl https://api.voltapi.online/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "gpt-4o",
"messages": [
{
"role": "user",
"content": "Hello, how are you?"
}
]
}'
Text Generation Models
VoltAI offers a comprehensive selection of text generation models from various providers.
OpenAI Models
- gpt-4o
- gpt-4o-mini
- gpt-4-turbo
- gpt-4.1
- gpt-4.1-nano
- gpt-4.5-preview
- chatgpt-4o-latest
- gpt-3.5-turbo
- gpt-oss-120b
- o3
- o3-mini
- o3-mini-pollination
- o4-mini
Claude Models
- claude
- claude-sonnet-4
- claude-sonnet-3.7-thinking
- claude-3.7-thinking
- claude-3.5-sonnet
- claude-3-7-sonnet-20250219
- claude-thinking
- claude-opus-4
- claude-opus-4.1t
- anthropic/claude-3-haiku
Grok Models
- grok-4
- grok-4-0709
- Grok-3-mini
Meta/Llama Models
- meta-llama/llama-guard-4-12b
- meta-llama/llama-3.2-3b-instruct
- llama-4-scout
Google Models
- google/gemini-2.5-flash-preview-05-20
- gemini-2.5-flash-lite-preview-06-17
- gemini-2.5-pro
- gemini-2.0-flash
DeepSeek Models
- DeepSeek-V3
- DeepSeek-R1-0528
Qwen Models
- qwen/qwen3-30b-a3b
- Qwen3-235B-A22B-Instruct-2507
- Qwen-2.5-Coder-32B
Mistral Models
- mistralai/mixtral-8x7b-instruct
- mistralai/mistral-nemo
- mistral-large
- devstral-small
Other Models
- microsoft/phi-4-reasoning-plus
- command-a
- kimi-k2
- sonar-reasoning
- sonar-reasoning-pro
- sonar-deep-research
Image Generation Models
Create stunning images with our FLUX models from Black Forest Labs.
FLUX Models
- black-forest-labs/FLUX.1-schnell
- black-forest-labs/FLUX.1-dev
- black-forest-labs/FLUX.1-kontext-pro
- black-forest-labs/FLUX.1-kontext-max
- black-forest-labs/FLUX.1-kontext-dev
Image Generation Usage
Use the /v1/images/generations
endpoint to generate images. Specify the model, prompt, and desired image size.
Embedding Models
Convert text into vector representations for semantic search and similarity tasks.
Available Embedding Models
- togethercomputer/m2-bert-80M-8k-retrieval
Embedding Usage
Use embedding models to convert text into high-dimensional vectors for:
- Semantic search applications
- Document similarity comparison
- Content recommendation systems
- Clustering and classification tasks
Pricing Plans
Choose the plan that best fits your needs. View our refund policy
Premium
- Access to Premium Models:
- ChatGPT-4o (Latest)
- GPT-4.5 Preview
- Claude 3.5 & 3.7 (Sonnet)
- claude-sonnet-4-20250514-thinking
- Claude Sonnet 4 (2025-05-14)
- GPT 5 NANO
- GPT 5 MINI
- GPT 5
- Gemini 2.5 Pro
- DeepSeek R1
- Kimi-K2
- Grok-4 (0709)
- FLUX.1 (Kontext Pro & Max)
- 20 requests/minute
- Daily limits:
- Claude models → 150 requests/day
- Other premium models → 2,000 requests/day
- Faster speeds and responses
Enterprise
- All Premium models included
- Usage Limits:
- Claude 4 Opus → 500 messages/day (80k context)
- Claude 4.1 Opus → 350 messages/day (80k context)
- All other premium models → 4000 messages/day
- 25 requests per minute
- Scalable Daily Limits
- You choose the limits, we calculate the monthly cost
- Context window can be increased
Our Refund Policy
We offer refunds under specific conditions to ensure fairness for all users. Read full refund policy →
Example Requests
Here are some examples to help you get started with the VoltAI API.
Basic Chat Completion
import requests
url = "https://api.voltapi.online/v1/chat/completions"
headers = {
"Authorization": "Bearer YOUR_API_KEY",
"Content-Type": "application/json"
}
data = {
"model": "gpt-4o",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "What is the capital of France?"}
]
}
response = requests.post(url, headers=headers, json=data)
print(response.json())
Using Claude Models
const response = await fetch('https://api.voltapi.online/v1/chat/completions', {
method: 'POST',
headers: {
'Authorization': 'Bearer YOUR_API_KEY',
'Content-Type': 'application/json'
},
body: JSON.stringify({
model: 'claude-3.5-sonnet',
messages: [
{
role: 'user',
content: 'Explain quantum computing in simple terms'
}
],
max_tokens: 500
})
});
const data = await response.json();
console.log(data.choices[0].message.content);
Image Generation with FLUX
curl -X POST https://api.voltapi.online/v1/images/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "black-forest-labs/FLUX.1-dev",
"prompt": "A serene landscape with mountains and a lake at sunset",
"n": 1,
"size": "1024x1024"
}'
Streaming Response
import requests
import json
url = "https://api.voltapi.online/v1/chat/completions"
headers = {
"Authorization": "Bearer YOUR_API_KEY",
"Content-Type": "application/json"
}
data = {
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Write a story"}],
"stream": True
}
response = requests.post(url, headers=headers, json=data, stream=True)
for line in response.iter_lines():
if line:
if line.startswith(b'data: '):
try:
chunk = json.loads(line[6:])
if chunk['choices'][0]['delta'].get('content'):
print(chunk['choices'][0]['delta']['content'], end='')
except:
pass
Rate Limits
Understanding our rate limiting helps you optimize your API usage.
Plan | Requests/Minute | Daily Limits |
---|---|---|
Free | 10 | 100 requests/day |
Premium | 20 | Claude: 150/day Others: 2,000/day |
Enterprise | 25 | Claude 4 Opus: 500/day Claude 4.1 Opus: 350/day Others: 4,000/day |
Rate Limit Headers
Each API response includes headers indicating your current rate limit status:
X-RateLimit-Limit
- Your rate limitX-RateLimit-Remaining
- Requests remainingX-RateLimit-Reset
- Time when the limit resets
Support
Need help? We're here to assist you.
Discord Community
Join our Discord server for real-time support and community discussions.
Join DiscordRefund Policy
We strive to provide the best AI API service. Please review our refund policy carefully before subscribing.
Policy Overview
This refund policy applies to all VoltAI API subscription plans. We aim to be fair while protecting our service from abuse.
Last Updated: January 2025
Non-Refundable Conditions
Refunds will NOT be issued under the following circumstances:
1. Usage Thresholds Exceeded
- If you have used a total of 50 requests or more
- If you have consumed 5 million tokens or more
- These limits apply cumulatively across all models and endpoints
2. Scheduled Maintenance
- Downtime due to announced scheduled maintenance
- Complaints about service unavailability during maintenance windows
- We provide advance notice for all scheduled maintenance
3. Terms of Service Violations
- Account suspension due to violation of our Terms of Service
- Abuse of API endpoints or rate limits
- Use of the service for prohibited activities
4. Change of Mind
- Simply changing your mind after purchase
- Finding a cheaper alternative
- No longer needing the service for personal reasons
Eligible for Refund
You MAY be eligible for a refund in these situations:
1. Complete Service Failure
- Unable to access ALL models for 24+ hours consecutively
- System-wide outage not related to scheduled maintenance
- Technical issues on our end preventing service usage
- Must be reported within 48 hours of the issue
2. Billing Errors
- Duplicate charges for the same subscription period
- Charged for a plan you didn't subscribe to
- Continued charges after cancellation confirmation
3. First 7 Days Guarantee
- New subscribers within first 7 days of initial purchase
- Must have used less than 50 requests AND less than 5M tokens
- Applies to first-time subscribers only
Refund Request Process
Submit Request
Contact our support team via Discord or email with your:
- API key (first and last 4 characters only)
- Subscription email
- Detailed reason for refund
- Evidence of service issues (if applicable)
Review Period
We will review your request within 3-5 business days. During this time:
- We may request additional information
- Your account usage will be audited
- Technical logs will be reviewed
Decision & Processing
If approved:
- Refund processed within 5-10 business days
- Funds returned to original payment method
- Account access may be terminated
Refund Calculations
Partial Refunds
In some cases, we may offer partial refunds:
- Pro-rated refunds: For extended service outages exceeding 48 hours
- Credit refunds: Service credits for future use instead of monetary refunds
- Plan downgrades: Difference refunded when moving to a lower tier
Important Notes
- All refund decisions are final and at our sole discretion
- Abuse of the refund policy may result in permanent account suspension
- Refunds do not include any third-party fees or charges
- This policy may be updated at any time without prior notice
- By subscribing, you acknowledge and agree to this refund policy
Contact Us
For refund requests or questions about this policy: