Set up your app
Where each app expects TokenReply
| App | Field | Value | Guide |
|---|---|---|---|
| JanitorAI | Proxy URL | https://api.tokenreply.com/v1/chat/completions | JanitorAI API setup |
| SillyTavern | Custom Endpoint (Base URL) | https://api.tokenreply.com/v1 | SillyTavern API setup |
| RisuAI | URL (Custom Models) | https://api.tokenreply.com/v1/chat/completions | RisuAI setup |
| Other apps | Base URL or endpoint | https://api.tokenreply.com/v1 | All roleplay platforms |
Why long context and cache matter for roleplay
- Every message resends the story. Roleplay apps send the character card, memory and recent chat history with each new message, so input tokens grow as the chat gets longer. On TokenReply, popular roleplay models recently averaged 14,000 to 23,000 input tokens per message.
- Cache makes long chats cheaper. Most of that input is the same from one message to the next. Models with a cached input price bill the repeated part at that lower rate; recently 50 to 77% of input tokens on popular roleplay models were served from cache.
- Long context keeps characters consistent. A larger context size lets the model see more of the story, at the cost of more input tokens per message. Pick the context size you need, not the largest possible.
- Automatic parameter clamping. Roleplay apps often send sampling values that some providers reject, such as a high temperature together with top_p and top_k. TokenReply adjusts these per model, so the defaults of JanitorAI and SillyTavern work.
Model picks by budget
Read from the live catalog when this page opens.
Access: Free models work on every account at no charge. Models of the week (Weekly Featured) allow 40 calls a day on Default and Trial accounts and have no daily cap on Plus. Plus models need a Plus subscription; calling them without one returns 403.
Free to try
Free models cost nothing per message and work on every account, subject to availability and rate limits.
| Model ID | Access | Input / 1M | Cached input / 1M | Output / 1M |
|---|---|---|---|---|
nvidia/nemotron-3-ultra-550b-a55b | Free | Free | Free | Free |
grok-4.20-fast | Free | Free | Free | Free |
nemotron-3.5-super-vl-free | Free | Free | Free | Free |
gemma-4-31b-it | Free | Free | Free | Free |
Low cost
Well under a cent for a typical long-chat message, and cheaper still when the chat history is cached.
| Model ID | Access | Input / 1M | Cached input / 1M | Output / 1M |
|---|---|---|---|---|
deepseek-v4-flash | Models of the week | $0.22 | $0.007 | $0.66 |
mimo-v2.5-pro | Models of the week | $0.217 | $0.0018 | $0.435 |
minimax-m2.5 | Models of the week | $0.09 | $0.009 | $0.36 |
glm-5.3-flash | Plus | $0.075 | $0.015 | $0.25 |
gemini-2.5-flash | Models of the week | $0.15 | $0.015 | $1.25 |
Balanced
Stronger writing and memory for long stories at a moderate price per message.
| Model ID | Access | Input / 1M | Cached input / 1M | Output / 1M |
|---|---|---|---|---|
kimi-k2.7 | Models of the week | $0.475 | $0.095 | $2 |
glm-5.2 | Models of the week | $0.7 | $0.13 | $2.2 |
glm-5.3 | Plus | $0.7 | $0.13 | $2.2 |
deepseek-v4-pro | Plus | $0.66 | $0.022 | $1.98 |
mimo-v2.6-pro | Plus | $0.217 | $0.0018 | $0.435 |
Premium
The most capable models for complex characters and long arcs. Plus accounts only.
| Model ID | Access | Input / 1M | Cached input / 1M | Output / 1M |
|---|---|---|---|---|
claude-sonnet-5 | Plus | $0.6 | $0.06 | $3 |
claude-opus-4-8 | Plus | $1.5 | $0.15 | $7.5 |
claude-opus-5 | Plus | $1.5 | $0.15 | $7.5 |
Cost per message
Read from the live catalog when this page opens.
Example: one message in a long chat sends 16,000 tokens (character, memory and history) and gets 800 tokens back. With cache, 12,000 of the 16,000 input tokens are the unchanged part of the chat and are billed at the cached input price. Free models cost nothing.
| Model ID | Per message | Per message with cache | 100 messages with cache |
|---|---|---|---|
deepseek-v4-flash | $0.00405 | $0.00149 | $0.149 |
mimo-v2.5-pro | $0.00383 | $0.00124 | $0.124 |
glm-5.3-flash | $0.0014 | $0.00068 | $0.068 |
kimi-k2.7 | $0.0092 | $0.00464 | $0.464 |
glm-5.2 | $0.013 | $0.00612 | $0.612 |
deepseek-v4-pro | $0.0121 | $0.00449 | $0.449 |
claude-sonnet-5 | $0.012 | $0.00552 | $0.552 |
claude-opus-4-8 | $0.03 | $0.0138 | $1.38 |
Prices use the cheapest available route, as on the models page. Actual cost depends on your context size, reply length and how much of the chat is cached.
Plans
What each plan includes for roleplay
| Plan | Roleplay models | Cost |
|---|---|---|
| Default | Free models, plus 40 Weekly Featured calls a day (10 more on check-in days) | Free; other usage from your wallet balance |
| Trial | Same models as Default, plus starter usage in the first month | Free for new accounts |
| Plus | Plus models without the Weekly Featured daily cap, higher rate limits and a larger context per request | $5 a month, with $5 of usage included |
Exact allowances are in plans and tiers. A daily check-in adds extra Weekly Featured calls for that day.
Troubleshooting
| Symptom | What it usually means | What to do |
|---|---|---|
The app reports a 404 or Invalid URL | The app expects a base URL but got the full endpoint, or the other way round. | JanitorAI and RisuAI take https://api.tokenreply.com/v1/chat/completions; SillyTavern and most other apps take https://api.tokenreply.com/v1. |
401 Invalid token | The key is incomplete, revoked, or pasted with spaces. | Copy the key again and paste it without spaces. |
403 or not permitted for a model | Your account tier does not include that model. | Pick a Free or Weekly Featured model, or upgrade to Plus. The tier of every model is shown on the models page. |
| 429 Too Many Requests | A rate limit or the daily Weekly Featured allowance was reached. | Wait a moment before retrying, or switch to another model. Plus has no daily Weekly Featured cap. |
502 or Service temporarily unavailable | The model is busy right now. | Retry the message. If it keeps failing, switch to another model from the list above and check status. |
Frequently asked questions
What is a roleplay API?
An API that roleplay apps such as JanitorAI, SillyTavern and RisuAI call to generate character replies. TokenReply exposes many models through one OpenAI-compatible endpoint, so you switch models by changing only the model ID.
Which roleplay apps work with TokenReply?
Any app with an OpenAI-compatible custom endpoint, including JanitorAI, SillyTavern, RisuAI and Agnai. See all roleplay platforms.
Can I use roleplay models for free?
Yes. Free models cost nothing per message, within rate limits, and Default and Trial accounts can also make 40 Weekly Featured calls a day.
How much does a long roleplay chat cost?
It depends on the model and the context size. The table on this page computes a typical long-chat message from live prices; on low-cost models it is well under one cent.
How do I pay for paid models?
Add balance on the top-up page (how to top up) and pay as you go, or subscribe to Plus for $5 a month, which includes $5 of usage and unlocks Plus models. Free models never need a balance.
Does one key work for every model?
Yes. One key reaches every model your account tier includes. Change the model ID in your app to switch.