Keys and models per provider. "Edit" loads one into the form below. Which ones answer the chat, and in what order, is set in Fallback order; "Use first" moves a provider to the top of it.
| Provider | Key | Model | Plan |
|---|
The chat asks the first provider; if it fails (error, timeout, empty answer) the next one takes over, within one 55-second budget. Providers without a key are skipped. Drag rows or use ↑ ↓, then save.
Applies to every provider.
When the bot cannot answer from the context, the chat shows this message and these buttons instead of the model's wording. Empty links are hidden.
| Button label | Link |
|---|
Shown as buttons under the chat. A click answers with this text instantly — no model call, no cost. Still recorded in the conversation history and counted by the rate limits.
reCAPTCHA v3 scores every message invisibly. Below the minimum score the chat shows the v2 "I'm not a robot" checkbox (if v2 keys are set); a passed checkbox trusts that conversation for 10 minutes. Keys come from google.com/recaptcha/admin — v3 and v2 are separate key pairs. Google accepts domains only (no IPs): with a bare IP, turn off "Verify the origin of reCAPTCHA solutions" in the key settings.
Everything the bot is allowed to answer from. Sent with every message (cached where the provider supports it).
Every message, user and assistant, including refused ones (rate limit, captcha, provider error).
| Last message | First question | Answered | Refused | Hand-offs | IP |
|---|
One row per model call (chat answers and admin tests), with the token counts the provider reported and the estimated cost at the prices in src/pricing.ts. FAQ answers make no call and do not appear here.
| Provider · model | Calls | Errors | Input | Cache read | Cache write | Output | Thinking | Neurons | Avg prompt | Avg time | Est. cost |
|---|
| Time | Source | Model | Input | Cache R/W | Output | Neurons | ms | Cost | Status |
|---|
Estimated from the current context size, measured per tokenizer. Prices as published on 2026-10-13 (USD per million tokens); always confirm on the provider's pricing page.
| Model | Input tok/msg | $ / message | 1,000 messages | 1,000 conversations | Per month | Your plan |
|---|
Public endpoints (/api/*) are what another website uses — they return the conversation only. Admin endpoints (/api/admin/*) need the x-api-key-admin-chatbot header. Every operation has a Try it form. (OpenAPI 3.1 — import into Swagger UI or Postman).