I still really like TokenReply, but it’s slowly losing it’s good models. It shows the availability for each model, and has fully unlimited ones. Though, some free models seem to get really unstable with high usage.

TokenReply has a general rate limit of 40 RPD (Requests per Day) for limited models, and a 3 RPM (Requests per Minute) limit for unlimited ones.

Setup

• Enter tokenreply.com
• Create an account and log in

Proxy URL

Paste it in the "Proxy URL" field on Janitor (mentioned in the Janitor Guide):

• Default: https://api.tokenreply.com/v1
• Modified (Sophia's Lorebary): (custom — check: Sophia’s Lorebary Guide)

API Key

Paste it in the "API Key" field on Janitor (mentioned in the Janitor Guide):

• Go to "Console" at the top
• Copy your API Key and paste it on Janitor

Note: After you create your account, you can use any model labeled as "Free" in the model list without any hard limits. However, sometimes there are a $1 claim you can take, or you can use the daily check-ins to add $0.01 to your wallet — which allow for you to use the "Weekly Featured" models.

Models

You can search for the available models on your own and test them, but here are my recommendations:

Free (Fully Unlimited):

• google/gemma-4-26b-a4b-it
• stepfun-ai/step-3.7-flash
• grok-4.3-high ****⚠️ currently giving errors