DeepSeek on Janitor AI. About 8,000 DeepSeek V4.1 Flash messages for $10.

Paste one proxy URL, a DeepSeek model ID and your key into Janitor AI's API Settings. One price at every hour, below DeepSeek's own, which doubles in weekday peak hours.

Your proxy settings

Proxy URL: https://api.apisrouter.com/v1/chat/completions
Model: deepseek-v4.1-flash
API key: sk-your-apisrouter-key

What 1,000 Janitor AI messages cost

Each message: about 8,000 tokens of character card and history in, 400 out, priced without caching on both sides. On these two models, a message here costs at least 13% less than on DeepSeek off-peak and 56% less than at its peak. DeepSeek's peak runs Monday to Friday, 01:00 to 04:00 and 06:00 to 10:00 UTC, except on Chinese public holidays. DeepSeek prices as listed on September 30, 2026.

  • DeepSeek V4.1 Flash (deepseek-v4.1-flash): DeepSeek, weekday peak: $2.88; DeepSeek, off-peak: $1.44; APIsRouter, any hour: $1.24; about 8,000 messages for $10
  • DeepSeek V4 Pro (deepseek-v4-pro): DeepSeek, weekday peak: $12.14; DeepSeek, off-peak: $6.07; APIsRouter, any hour: $5.00; about 2,000 messages for $10

Set it up in one minute

  • Get a key: Start on the $2 trial credit, or top up from $10 below and the key arrives by email.
  • Open API Settings: In any chat on Janitor AI, open API Settings and switch from the default model to Proxy.
  • Fill in the three fields: Paste the proxy URL and your key, and type deepseek-v4.1-flash or deepseek-v4-pro as the model. The URL must end in /chat/completions.
  • Save and say hello: Save, refresh the chat and send a short message.

If it does not answer

  • model_not_found: Type deepseek-v4.1-flash or deepseek-v4-pro exactly, in lowercase. A model ID copied from another provider's guide can fail with this error.
  • 404: If the error does not say model_not_found, the proxy URL stops at /v1: add /chat/completions to the end.
  • 401: The key is incomplete or has a space at either end. Paste it again.

Two ways to pay

Both fill one balance, spent as you chat.

FAQ

How do I use DeepSeek on Janitor AI?

Open API Settings in a chat and switch to Proxy. Paste https://api.apisrouter.com/v1/chat/completions as the URL, type deepseek-v4.1-flash as the model, paste your key, then save and refresh the chat.

Is DeepSeek on Janitor AI free?

You can start on the $2 trial credit, about 1,600 DeepSeek V4.1 Flash messages: sign in and claim it from your dashboard, no card needed. After that, top up from $10.

Which DeepSeek model is best for Janitor AI?

DeepSeek V4.1 Flash for everyday chats, at the lowest cost per message. DeepSeek V4 Pro for scenes that need more thought, at a higher cost per message, as the table shows. Switching is one field in API Settings.

Why not use DeepSeek's own API?

You can. DeepSeek's own price doubles in its weekday peak hours. APIsRouter charges one price at every hour, below DeepSeek's off-peak price, and the same key also runs Gemini and Claude.

When are DeepSeek peak hours?

Monday to Friday, 01:00 to 04:00 and 06:00 to 10:00 UTC, except on Chinese public holidays, on DeepSeek's own API. APIsRouter does not change its price by the hour.

Can I switch to Claude or Gemini later?

Yes. Change the model in API Settings to a Claude or Gemini ID; the proxy URL and key stay the same.

Do unused credits expire?

No. Credit stays in your balance until you use it, and requests stop when it runs out, so there are no surprise bills.