Tutorial

Tutorial posts from the AIHubMix team.

• 

  Moving to Gemini 4 Argon from Gemini 3.1 Pro or 3.8 Flash: What Breaks and How to Fix It

  Gemini 4 Argon became generally available on October 13, 2026, under the model ID gemini-4-argon, on the paid Gemini API, on Vertex AI and on AIHubMix. AIHubMix lists it at $2 per million input tokens, $10 per million output tokens and $0.10 per million cached input tokens, the same as Google's introductory rate. Google's rate runs until November 30; from December 1 it doubles to $4 and $20. Changing the model string is the easy part. Google's What's new in Gemini 4 Argon page ends with a migr

  October 14, 20269 min readTutorial
• 

  Gemini 4 Argon Thinking Levels and Long Decode: Defaults, Costs and When to Use Each

  Gemini 4 Argon became generally available on October 13, 2026, and with it Google documented the two settings that decide what an Argon request costs and how long it takes: the thinking level and the output limit. Argon offers three thinking levels, low, medium and high, and defaults to medium. Responses stop at 64K tokens unless you turn on long decode, which lets a single response run to 1M tokens. There's a catch in the defaults. Every published Argon benchmark ran at high: Google evaluated

  October 14, 20268 min readTutorial
• 

  AIHubMix Supports JanitorAI Roleplay Chat, with Zero Data Retention on by Default

  AIHubMix supports roleplay chat. Connect it to JanitorAI as a proxy, pick a free model, and your characters reply through AIHubMix. Every AIHubMix account also has Zero Data Retention (ZDR) turned on by default, so we don't log, store, or keep your messages, your character prompts, or the model's replies. The short version: * Roleplay chat: AIHubMix connects to JanitorAI as a proxy. Dozens of free models are available, and our first pick for roleplay chat is xiaomi-mimo-v2.6-pro-free. * Ze

  October 13, 20265 min readTutorial
• 

  Which AIHubMix Free Model to Use for JanitorAI Roleplay

  Update (October 23, 2026): xiaomi-mimo-v2.5-pro-free was retired on 21 October 2026 and now returns 404 model_retired. If a saved configuration still uses it, switch the Model field to xiaomi-mimo-v2.6-pro-free. Short answer: start with xiaomi-mimo-v2.6-pro-free, save one or two general chat models as backups, and keep low-cap and coding models out of long sessions. Treat that as a starting point, not a ranking. There's no official roleplay benchmark for AIHubMix's free models, and none of the

  October 13, 20266 min readTutorial
• 

  AIHubMix Free Model Limits for JanitorAI: 10 Trial Calls, the $1 Unlock, and the Token Cap

  A new AIHubMix account gets 10 trial calls in total, shared across every free model. They are not 10 per day or one every few minutes. A one-time top-up of $1 or more switches the account to daily quotas: 100 requests a day, 10 a minute, and 1M tokens a day, shared across the whole free catalog. For long JanitorAI chats, the 1M-token pool is usually what runs out first, well before you reach 100 replies. The rest of this guide explains each limit, shows how fast a JanitorAI chat uses the token

  October 13, 20266 min readTutorial
• 

  How to Pay on AIHubMix with Alipay

  To unlock AIHubMix's free models for everyday use, you need one top-up of $1 or more. The $1 amount works through the Alipay option on the top-up page, paid from the Alipay app. Card checkout through Stripe, including the Alipay button inside the Stripe checkout, starts at $15. After any top-up of $1 or more, the AIHubMix free models page says your account "permanently" switches to daily quotas: 100 requests a day, 10 a minute, and 1M tokens a day across all free models. It's a one-time step,

  October 13, 20267 min readTutorial
• 

  How to Use AIHubMix Free Models in JanitorAI: Proxy Setup and Common Errors

  JanitorAI can talk to any OpenAI-compatible API through its Proxy option, and AIHubMix is one. The whole setup is four values typed into one form: Name: anything you like, e.g. AIHubMix MiMo Proxy URL: https://aihubmix.com/v1/chat/completions API key: your AIHubMix key Model: xiaomi-mimo-v2.6-pro-free Leave Custom prompt empty, press Test, then Add, and refresh the page. That's it. Most failures reported in the JanitorAI community come from one of those four fields being sl

  October 13, 20268 min readTutorial
• 

  Codex Compaction Fails With "response protection is unavailable": It's the Web Search, Not Your Context

  Since October 8, 2026, long Codex sessions have been dying the moment they try to compact. The error reads stream disconnected before completion: response protection is unavailable, retries don't help, and the conversation can't continue. Most reports involve gpt-6.1-sol, but gpt-6-astra and gpt-5.6-sol fail the same way. It shows up behind self-hosted proxies, and it also shows up in the official Codex app with a direct ChatGPT login. The short answer: the context isn't too big, and your netw

  October 10, 20268 min readTutorial
• 

  Migrating from Claude Haiku 4.5 to 5.5: Five 400 Errors and the Quiet Changes

  Changing claude-haiku-4-5 to claude-haiku-5-5 is the smallest part of this migration. Five request patterns that worked on Haiku 4.5 now return a 400 error, and several more changes fail no request but alter what you get back, what it costs, or how the model behaves inside an agent. Anthropic says existing Haiku 4.5 prompts should work well on Haiku 5.5 without changes. The request code around those prompts is a different story. This post lists each problem as you'll meet it: what you'll see,

  October 8, 20269 min readTutorial
• 

  Claude Haiku 5.5 Effort Levels: Medium Is the Default, Low Is Often Enough

  Claude Haiku 5.5 is the first Haiku with an effort setting, and the setting moves the bill more than anything else you control. In Artificial Analysis's independent runs, Haiku 5.5 at max effort scored 43 on its Intelligence Index and at low effort scored 29. Max also used 440 million output tokens to get through the index; low used 32 million. So the short answer: leave most work at the default, medium. Drop high-volume, simple routes to low. Raise knowledge work and strict instruction follow

  October 8, 20268 min readTutorial