Llama 4 Maverick
Open-weight and very economical. Made by Meta, served via OpenRouter, available in Knecty alongside every other model on one subscription.
At a glance
- Made by
- Meta
- Served via
- OpenRouter
- Tier
- Fast
- Input
- Text
- Context window
- 1M tokens
- Longest reply
- 16K tokens
- Extended thinking
- No
- Where
- Every region Knecty serves
What it costs
- Input, per 1M tokens
- $0.25
- Output, per 1M tokens
- $1.00
You pay for the tokens each reply actually uses, at OpenRouter’s price plus the 25% platform fee. Before you send, the composer shows an estimate, and every reply shows what it cost.
Usage comes out of the credit included with your plan, then any top-up. See plans and every model’s price.
The model you pick is the model that answers
Every reply is labeled with the model that actually wrote it. If Llama 4 Maverick can’t answer and Knecty uses another model, the reply says so.
Read more: The "Served by" guarantee · Models available in your region · Help centre · Pricing
Try Llama 4 Maverick for 7 days
The same subscription covers every other model too. Switch per message whenever you like.
Model names and logos are trademarks of their respective owners. Knecty is an independent service and is not affiliated with or endorsed by them.