CompanionScout
Tool

AI Proxy Cost Calculator for Janitor AI & SillyTavern

At 60 messages a day with an 8k-token context, DeepSeek Flash costs about $5 a month; a light user sending 10 short messages a day pays under $1. The bill is driven less by your messages than by the context resent with each one: the character card, persona, lorebook and chat history. Pick a model below, set how much you chat, and the estimate updates live with prices checked 2026-10-29 from each provider’s official pricing page.

What will my proxy cost per message and per month?

Prices checked 2026-10-29 from each provider’s official pricing page (sources below). Estimates assume every swipe resends the full context and exclude tax. A 1,000-token reply is roughly 750 English words. Nothing you enter leaves your browser.

Proxy doctor: what does this error mean?

Paste the error your proxy shows (for example “429”, “failed to fetch” or “model not found”).

All common proxy errors
401 Unauthorized / invalid API key
Cause: The key is wrong, revoked, or pasted with a space or line break. Fix: Create a fresh key in the provider dashboard, paste it again with no spaces, and check it belongs to the same provider as the endpoint URL.
402 Payment required / insufficient balance
Cause: Your balance is empty or negative for a paid model. Fix: Top up the provider balance, or switch to a free model. On OpenRouter, a top-up of 10 credits also lifts the free-model cap from 50 to 1,000 a day.
403 Forbidden
Cause: The key does not have access to this model, the account is restricted, or the model is unavailable in your region. Fix: Check the model is enabled for your account and region in the provider dashboard, or pick another model.
404 Not found / model not found
Cause: The model ID is misspelled, retired, or the endpoint URL is wrong. Fix: Copy the exact model ID from the provider’s model list (IDs are case-sensitive), and make sure the URL ends in /chat/completions.
429 Too many requests / rate limited
Cause: You hit a per-minute or per-day cap. OpenRouter free models allow 20 a minute and 50 a day (1,000 a day after buying 10 credits). Busy upstream providers also return 429. Fix: Wait and retry, slow down swipes, try another free model, or add credit. Each swipe counts as a request.
5xx / overloaded / timeout
Cause: The upstream provider is down, overloaded or slow; it is not your settings. Fix: Retry in a few minutes or switch provider. Large contexts make timeouts more likely, so trimming chat memory helps.
“Failed to fetch” / network error
Cause: The request never reached the provider: usually a wrong endpoint URL, a typo in https, or a browser extension or network blocking it. Fix: Re-check the full endpoint URL (for example https://openrouter.ai/api/v1/chat/completions), disable blockers for the site, and try another network.
Context length exceeded
Cause: Character card + persona + memory + chat history is larger than the model or your settings allow. Fix: Lower the context size, shorten the character card or lorebook, or start a new chat with a summary.
Empty or cut-off replies
Cause: The reply-length (max tokens) setting is too low, or a reasoning model spent its tokens thinking. Fix: Raise max new tokens, or turn reasoning off for chat models that support it.
Refusals / content blocked
Cause: The model or provider’s content policy declined the request. This is policy, not a bug. Fix: Pick a provider whose published usage policy fits what you use it for. We don’t publish ways around provider safety rules.

How the estimate works

Cost per request is the context tokens times the input price, plus the reply tokens times the output price, divided by one million. Swipes resend the same context, so each one is charged as another request. DeepSeek bills cached input at a much lower rate and charges double during its weekday peak hours; Gemini 3.8 and 3.6 Flash double their paid prices on 1 January 2027, and the estimator warns you before that applies.

Free routes trade money for limits. OpenRouter’s free models are capped per minute and per day, and the free tiers on Google’s Gemini API are rate-limited per account. Janitor AI’s own model is free; its janitor+ subscription adds context and speed.

Want the costs of companion apps instead of proxies? Use the pricing index for what each app’s free tier and paid plans include, or the credit cost calculator for token and credit packs. Setting up a proxy for the first time? Start with our Janitor AI proxy guide.

Sources

Frequently asked questions

How much is 1,000 tokens in dollars?

It depends on the model. On DeepSeek Flash's direct API, 1,000 input tokens cost $0.00015 off-peak and 1,000 output tokens $0.0006 (prices checked 2026-10-29). Because every message resends your character card and chat history, the input side usually costs more than the reply.

Is OpenRouter free for Janitor AI?

Its :free models cost nothing per token but are capped at 20 requests a minute and 50 a day. Buying 10 credits once lifts the cap to 1,000 a day. OpenRouter charges a 5.5% fee (minimum $0.80) on credit purchases. Each swipe counts as a request.

Why does my proxy not work?

Most failures are a wrong endpoint URL ("failed to fetch"), a mistyped model ID (404), a bad or empty key (401 or 402), or a rate limit (429). Paste your error into the proxy doctor above for the likely cause and fix.

Is a proxy cheaper than janitor+?

Often, at light use. janitor+ is $12.99 a month or $99 a year and covers the built-in model with 5× the free context; Router and outside API keys are billed per token on top. Enter your daily messages above to compare.