Models
Ranus models are built for different workloads, from fast and efficient tasks to advanced reasoning. Every plan includes the full Ranus model family.
Fast
Cepat & hemat
Fast and cost-efficient Ranus model for lightweight tasks and high-volume workloads.
Best for
"model": "ranus-fast"
Smart
Default production
Balanced Ranus model for production applications and everyday AI features.
Best for
"model": "ranus-smart"
Reason
Advanced reasoning
Advanced Ranus model for complex reasoning, coding, long-context analysis, and technical problem solving. Supports up to 1,000,000 tokens of context window with 128,000 max output tokens.
Best for
"model": "ranus-reason"
Token vs credit
Definition
1 credit = 1,000 tokens
Measured against the ranus-fast baseline. Other models use multipliers to determine how many credits are consumed.
Formula
credit = (input_tokens / 1000 × inputMultiplier)
+ (output_tokens / 1000 × outputMultiplier)Example: ranus-reason
Calculator
Estimate credit usage based on model selection and token volume.
Per request
2.000 credits
Total request per plan
Basic
5,000
Pro
25,000
Max
50,000
Token equivalent per plan
Estimated token volume per plan based on monthly credits with a 50% input / 50% output split.
| Plan | Monthly credits | ranus-fast | ranus-smart | ranus-reason |
|---|---|---|---|---|
| Basic | 10,000 | 10M tokens | 6.7M tokens | 4M tokens |
| Pro | 50,000 | 50M tokens | 33.3M tokens | 20M tokens |
| Max | 100,000 | 100M tokens | 66.7M tokens | 40M tokens |
Choose your plan, create an API key, and start building with Ranus models in minutes.