Start free forever. Scale when you need to. No hidden fees.
See All PlansAlways free, forever!
Perfect for exploring premium models.
For a better experience.
Ideal for power users.
Next-level experience.
Top tier plan, all models unlocked!
These special plans are built for extreme power users who push far beyond normal limits, offering the same features with massively higher quotas and concurrency.
| Feature | Basic | Standard | Plus | Pro | Elite | Ultimate |
|---|---|---|---|---|---|---|
| Price | Free | $3/mo | $6/mo | $10/mo | $13/mo | $17/mo |
| Free model requests/day | ∞ | ∞ | ∞ | ∞ | ∞ | ∞ |
| Premium model requests/day | 50 | 800 | 1,600 | 2,800 | 3,700 | 5,000 |
| Concurrent requests | 1 | 1 | 1 | 5 | 10 | 15 |
| AI Models access | 100+ | 100+ | 100+ | 100+ | 100+ | 100+ |
| Enhanced chat memory | ✓ 3x | ✓ 5x | ✓ 10x | ✓ 15x | ✓ 20x | ✓ 25x |
| Support | Community support | Premium support | Unlock GPT 5 + Gemini 2.5 Pro | Unlock Gemini 3 Pro + Claude Haiku | Unlock Claude Sonnet | Unlock Claude Opus |
Understand how we measure request usage across different models and context sizes.
The daily request limits shown on every plan above are calculated assuming model cost = 1 and optimization cost = 1. In other words, these numbers assume standard-cost requests under 15,000 tokens.
In practice, request cost depends on the type of model you use:
1. Regular models (non full-context)For regular models, the actual cost is calculated using the formula:
Model cost depends on which model you use. Cheap models have a model cost of 1, while more expensive models such as GLM, Gemini, and Claude have a higher model cost per request. You can read more about the cost of each model in the "Available Models" menu.
Optimization cost starts at 1 for the first 15,000 tokens of a request and increases by 1 for every additional 5,000 tokens. For example:
For full-context models, the cost is calculated using model cost only. The optimization cost is always 1, regardless of the request size or context window.
Join thousands of developers using LiteRouter to access AI models effortlessly.
Get Started Free