Pricing
CompactifAI Pricing
Section titled “CompactifAI Pricing”CompactifAI offers simple, transparent pay-as-you-go pricing for our API services.
Overview
Section titled “Overview”Our pricing is based on tokens processed through the API. We charge separately for:
- Input tokens: Text sent to the API
- Cached input tokens: Input tokens served from the prompt cache, billed at a reduced rate (see Prompt Caching)
- Output tokens: Text generated by the API
A token represents approximately 4 characters or 0.75 words in English.
Model Pricing
Section titled “Model Pricing”| Model | Input (per 1M tokens) | Cached input (per 1M tokens) | Output (per 1M tokens) |
|---|---|---|---|
| carina-60b | $0.05 | - | $0.20 |
| qwen-3-8-27b | $0.40 | - | $2.00 |
| glm-5-2 | $1.10 | $0.22 | $3.50 |
| glm-5-3 | $1.10 | $0.22 | $3.50 |
| quasar-2-358b | - | - | - |
A dash (-) means prompt caching is not enabled for that model, so all input tokens are billed at the standard input rate.
Prompt Caching
Section titled “Prompt Caching”Cached input tokens are a subset of a request’s input tokens: the cached portion is billed at the cached rate and the remainder at the standard input rate.
Usage with glm-5-3: 1M input tokens, of which 800K are served from the cache, + 100K output tokensCost calculation:- 200K non-cached input tokens × $1.10 per 1M = $0.22- 800K cached input tokens × $0.22 per 1M = $0.176- 100K output tokens × $3.50 per 1M = $0.35
Total cost: $0.746Speech-to-Text Pricing
Section titled “Speech-to-Text Pricing”| Model | Price (per audio minute) | Billing Granularity |
|---|---|---|
| cai-whisper-large-v3-turbo-slim | $0,000134 | Per-second billing with 1-minute minimum |
Pay-as-you-go
Section titled “Pay-as-you-go”- Pay only for what you use
- No monthly commitments or minimum fees
- Billing based on actual token usage
Billing Example
Section titled “Billing Example”Usage: 5M input tokens + 2M output tokens with carina-60bCost calculation:- 5M input tokens × $0.05 = $0.25- 2M output tokens × $0.20 = $0.40
Total cost: $0.65Monitor Your Usage
Section titled “Monitor Your Usage”- Use the CompactifAI Dashboard to manage API tokens, monitor usage, view account settings, and review billing.
How do I estimate my token usage? A token represents approximately 4 characters or 0.75 words in English. For more specific estimations, contact our support team.
How often will I be billed? Billing occurs monthly based on your actual usage.
Is there a minimum spend requirement? No, you only pay for what you use.
Contact Us
Section titled “Contact Us”For questions about pricing or to request a custom enterprise plan, please contact our sales team.