Step 1: Create an account and an API key
- Create a free TokenReply account.
- Create an API key on the API keys page (walkthrough) and copy the value that starts with
sk-.
Step 2: Connect SillyTavern
- Open API Connections (the plug icon) and set API to Chat Completion.
- Set Chat Completion Source to Custom (OpenAI-compatible).
- Set Custom Endpoint (Base URL) to
https://api.tokenreply.com/v1. Do not add/chat/completions; SillyTavern adds it. - Paste your key into Custom API Key and select Connect.
- Choose a model from the list. TokenReply returns every model your key can use; you can also type an exact ID.
- Select Test Message to confirm the connection.
Step 3: Context size, response length and streaming
These settings are in AI Response Configuration (the sliders icon at the top left).
Recommended SillyTavern settings
| Setting | Recommended value | Why |
|---|---|---|
| Context Size (tokens) | 16384 to 32768 for most chats | SillyTavern sends history up to this size with every message. Larger contexts remember more but cost more per message. |
| Max Response Length (tokens) | 600 to 1000 | Enough for a full reply. Avoid 0 or extreme values: a few models reject them with a 400 error. |
| Streaming | On | Text appears as it is written, and long replies are not cut off by the 2 minute limit on replies sent all at once. |
| Temperature | 0.8 to 1.0 to start | TokenReply adjusts sampling values a model's provider would reject, so SillyTavern's sliders do not cause errors. |
Step 4: Choose a model
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 |
What does one message cost?
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.
Troubleshooting
| Symptom | What it usually means | What to do |
|---|---|---|
| The model list is empty | The endpoint is not the base URL, or the key was not accepted. | Set the endpoint to exactly https://api.tokenreply.com/v1, paste the key again, select Connect, then type an exact model ID if needed. |
401 Invalid token | The key is incomplete, revoked, or pasted with spaces. | Copy the key again from the API keys page and paste it into Custom API Key. |
503 No upstream channel is available for this model | The model ID is misspelled, has a trailing space, or is not in the catalog. | Pick the model from the list instead of typing it, or copy the exact ID from the models page. |
400 The request failed with status code 400 | Usually Max Response Length is 0 or very large, or the prompt is longer than the model's context window. | Set Max Response Length to 600 to 1000 and lower Context Size. |
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. |
| A status warning appears but chats work | SillyTavern's status check is stricter than a chat request. | Enable Bypass API status check and rely on a successful Test Message. |
Frequently asked questions
Which SillyTavern API type should I use with TokenReply?
Chat Completion with the Custom (OpenAI-compatible) source and the base URL https://api.tokenreply.com/v1.
Should I paste the full /chat/completions URL into SillyTavern?
No. SillyTavern asks for a base URL and adds /chat/completions itself, so use https://api.tokenreply.com/v1.
What context size should I use in SillyTavern?
16384 to 32768 tokens suits most chats. Larger contexts keep more of the story but send more tokens with every message; models with a cached input price make the repeated part cheaper.
Does streaming work?
Yes. Keep Streaming on; it also avoids the time limit on replies sent all at once.
Can one key switch between free and paid models?
Yes. The endpoint and key stay the same; which models work depends on your account tier and balance.