Credits
qualcode.ai uses a credit-based system that reflects the actual cost of AI processing. This transparent approach lets you predict costs and choose the quality level appropriate for your research.
How Credits Work
Credits are consumed each time you run a coding job. The number of credits required depends on three factors: the number of responses, the model quality tier, and the amount of context (training data) you provide.
Credits are deducted at the start of each run. If a run is cancelled or fails partway through, unused credits are automatically refunded based on the number of responses that were not processed.
Credit Formula
The credit cost for a coding run is calculated as:
credits = responses x model_factor x context_factor| Component | What It Represents | Range |
|---|---|---|
responses | Number of responses to code | 1 - 50,000 |
model_factor | Quality tier multiplier | 1.0x - 5.0x |
context_factor | Training data size multiplier | 0.8x - 2.0x |
Model Tiers
Choose the quality tier that matches your research needs. Higher tiers use more capable (and more expensive) AI models.
| Tier | Factor | Models | Best For |
|---|---|---|---|
| Budget | 1.0x | GPT-4.1 Nano, Claude Haiku | Simple categories, exploratory coding, high volume |
| Standard | 1.5x | GPT-4.1 Mini, Claude Haiku 4.5 | Default tier, good balance of cost and quality |
| Quality | 3.0x | GPT-4.1, Claude Sonnet 4.5 | Complex categories, nuanced responses, publication-ready |
Start with Standard. For most research, Standard tier provides excellent results. Only upgrade to Quality if you're seeing lower-than-expected agreement rates or have particularly nuanced categories.
Context Factor
The context factor reflects the cost of processing training data (examples you provide to guide the AI). More training data generally improves accuracy but increases cost.
| Training Data Size | Factor | Description |
|---|---|---|
| Minimal | 0.8x | 10,000 tokens or fewer (zero-shot or few examples) |
| Standard | 1.0x | 10,000 - 20,000 tokens (typical training set) |
| Medium | 1.5x | 20,000 - 40,000 tokens (extensive examples) |
| Large | 2.0x | 40,000 - 60,000 tokens (maximum context) |
What's a token? Roughly 4 characters or 0.75 words in English. A typical training example of 50 words is about 65 tokens. The qualcode.ai interface shows your training data size before you start a run.
Example Calculations
Here are some common scenarios to help you estimate costs:
Small Study, Standard Settings
500 responses x 1.5 (Standard) x 1.0 (Standard context) = 750 creditsLarge Study, Budget Model, No Training Data
5,000 responses x 1.0 (Budget) x 0.8 (Minimal) = 4,000 creditsMedium Study, Quality Model, Extensive Training
1,000 responses x 3.0 (Quality) x 1.5 (Medium context) = 4,500 creditsPublication-Critical Study, Maximum Quality
2,000 responses x 5.0 (Premium) x 1.0 (Standard context) = 10,000 creditsSee exact costs before running: The coding run dialog shows the exact credit cost based on your settings before you confirm. No surprises.
Free Credits
Every new qualcode.ai account receives up to 500 free credits:
- 50 credits immediately upon registration
- +450 credits after verifying your email address
This is enough to code approximately 330 responses at Standard quality, or 500 responses at Budget quality - plenty to test the platform with your own data before purchasing.
No credit card required. Sign up and start coding immediately with your free credits. Verify your email to unlock the full 500 credits.
Getting More Credits
When you need more credits than the free tier provides, contact us for pricing information.
Credits never expire. Buy once, use whenever you need them. There's no subscription or monthly fee.
Auto-Suggest Credits
The Auto-Suggest Coding Guide feature has separate pricing from coding runs. Auto-suggest always uses premium models (GPT-5.2 and Claude Opus 4.5) for the highest quality category suggestions.
| Mode | Base Cost (300 samples) | Description |
|---|---|---|
| Quick | 15 credits | Direct dual-rater analysis with high reasoning effort |
| Thorough | 45 credits | Multi-phase analysis with maximum reasoning (3x multiplier) |
Cost scales linearly with sample size. Formula: max(5, 15 × (sample_size / 300) × mode_factor)
No model tier selection for Auto-Suggest. Unlike coding runs, Auto-Suggest always uses our most capable models to ensure high-quality category suggestions.
Credit Refunds
Credits are refunded automatically in these situations:
- Cancelled runs: Unprocessed responses are refunded immediately
- Failed runs: If a system error prevents completion, unprocessed responses are refunded
- Rejected responses: Pre-filtered responses (empty, spam) are not charged
Successfully processed responses are not refunded. Once a response has been coded by both AI raters, those credits have been consumed. Review your settings carefully before starting large runs.
Tracking Your Usage
Monitor your credit balance and history:
- Dashboard header: Current balance always visible
- Transaction history: Complete record of credits earned, spent, and refunded
- Per-run costs: Each coding run shows its credit cost
Related: Learn about the Dual-Rater Methodology that powers qualcode.ai.