Basics
TextMate AI limits usage with a rolling 4-hour token window, not a daily reset. The window starts at your first message and expires exactly 4 hours later, at which point a new window begins.
| Plan | Tokens per 4-hour window |
|---|---|
| Free | 500,000 |
| Pro | 1,000,000 (2x Free) |
Tokens count both what you send and what the model generates.
| Free | Pro | |
|---|---|---|
| Price | ₹0/mo | From ₹41/mo (billed yearly) |
| Usage window | 500,000 tokens / 4h | 1,000,000 tokens / 4h |
| Models | Mistral Large, GPT-OSS 20B | All 7 models (+ DeepSeek V3.1, GLM 4.7, Llama 3.3 70B, Nemotron 3 Ultra, Gemma 4 31B) |
| Context window | Standard | Maximum |
| Server access | Standard | Priority |
| Agents & tools | Basic | Advanced |
Full pricing tiers (monthly / 6-month / yearly) are on the Pricing page.
Once a window's token budget is used, new messages are blocked until the window rolls over (up to 4 hours from your first message in that window). Upgrading to Pro raises the ceiling 2x and unlocks the remaining 4 models.
See How the Rolling Window Works for the full explanation with examples.