Pricing
All Ranus models.
Clear credits.
Every plan includes access to the Ranus model family. Use faster models for scale, or advanced reasoning models for deeper tasks. Credits are transparent, predictable, and easy to monitor.
Basic
per month
- ≈ 10,000,000 token-equivalent on ranus-fast
- Access to all Ranus models
- 30 requests/minute
- Output token limit based on selected model
- Advanced models use more credits
Pro
Popularper month
- ≈ 50,000,000 token-equivalent on ranus-fast
- Access to all Ranus models
- 120 requests/minute
- Output token limit based on selected model
- Advanced models use more credits
Max
per month
- ≈ 100,000,000 token-equivalent on ranus-fast
- Access to all Ranus models
- 300 requests/minute
- Output token limit based on selected model
- Advanced models use more credits
1 credit = 1,000 tokens · multiplier: fast 1x/1x · smart 1x/2x · reason 2x/3x
Credit System
One balance,
all Ranus models.
Use one credit balance across the Ranus model family. Faster models are efficient for scale, while reasoning models use more credits for deeper, more complex tasks.
1x · 1x
max output 4,096 tokens
Fastest and most cost-efficient Ranus model. Best for classification, extraction, short summaries, simple chat, and high-volume workloads.
1x · 2x
max output 32,768 tokens
Balanced Ranus model for most production apps. Ideal for assistants, customer support, content generation, and workflow automation.
2x · 3x
max output 128,000 tokens
Advanced Ranus model for complex reasoning, long-context analysis, document understanding, coding, and planning.
Example
Model: ranus-reason Input: 2,000 tokens Output: 1,000 tokens input credit = 2,000 / 1,000 × 2 = 4 output credit = 1,000 / 1,000 × 3 = 3 total = 7 credits