Skip to main content
VoidAI uses a credit-based billing system. You spend credits when making API requests, and the cost depends on the model and tokens used.

​
How Credits Work

For most models (chat, completions): 
credits = total_tokens × model_multiplier
For fixed-cost models (images, audio, video): 
credits = fixed_base_cost

​
Model Multipliers

Different models have different multipliers based on their capabilities and costs:

​
Chat Models

ModelMultiplierPlan
gpt-4.1-nano0.1All
gpt-4o-mini0.25All
gpt-5.10.75All
gpt-4o1.25All
o3-mini0.25All
o30.5Basic+
o15.0Premium+
claude-3-5-haiku-202410221.0All
claude-sonnet-4-5-202509291.75Basic+
claude-opus-4-5-202511014.0Basic+
gemini-2.0-flash0.5All
gemini-2.5-pro1.0All
deepseek-v30.1All
deepseek-r10.35All
lumina0.3All

​
Fixed Cost Models

ModelCreditsType
gpt-image-12,000Image generation
imagen-3.0-generate-0022,500Image generation
flux-kontext-pro3,000Image generation
midjourney75,000Image generation
text-embedding-3-small50Embeddings
text-embedding-3-large50Embeddings
tts-175Text-to-speech
tts-1-hd150Text-to-speech
whisper-110Transcription
sora-25,000Video generation
sora-2-pro15,000Video generation
omni-moderation-latest0Moderation (free)

​
Example Calculation

If you send a request using gpt-5.1 (multiplier: 0.75) with:
  • Input tokens: 1,000
  • Output tokens: 500
  • Total tokens: 1,500
Credits charged: 1,500 × 0.75 = 1,125 credits

​
Plans

Different plans have access to different models:
PlanAccess
FreeBasic models (gpt-4o-mini, gemini-2.0-flash, etc.)
Basic+ Claude Sonnet, o3, Sora
Premium+ Claude Opus, o1, Premium image models
Pro/UltraAll models including Midjourney

​
Checking Your Balance

Your current credit balance is available in your dashboard.

​
Discounts

VoidAI offers personalized daily discounts on select models. When you have an active discount: 
discounted_credits = credits / discount_multiplier
For example, with a 2x discount on a model:
  • Normal cost: 1,000 credits
  • Discounted cost: 500 credits
Check your active discounts via the My Discounts endpoint.

​
Rate Limiting

In addition to credits, there’s a rate limit of 100 requests per minute per API key. If exceeded, you’ll receive a 429 Too Many Requests error. 
from openai import OpenAI, RateLimitError
import time

client = OpenAI(
    api_key="sk-voidai-your_key_here",
    base_url="https://api.voidai.app/v1"
)

def request_with_retry(messages, max_retries=3):
    for attempt in range(max_retries):
        try:
            return client.chat.completions.create(
                model="gpt-5.1",
                messages=messages
            )
        except RateLimitError:
            if attempt < max_retries - 1:
                time.sleep(2 ** attempt)
            else:
                raise

response = request_with_retry([{"role": "user", "content": "Hello!"}])

​
Tips to Optimize Costs

Choose the right model

Use smaller models (gpt-4o-mini, deepseek-v3) for simple tasks. Save premium models for complex work.

Use discounts

Check your daily discounts and time high-volume work accordingly.

Cache responses

Cache responses for repeated identical queries to avoid duplicate costs.

Optimize prompts

Shorter prompts = fewer input tokens = lower costs.