AIHubMix Blog

Announcements, tutorials, model analysis, and product updates from AIHubMix.

• 

  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
• 

  What Is Mistral Large 4? A Trillion-Parameter Specialist from Europe

  Mistral Large 4 is Mistral AI's new flagship. It has about one trillion parameters, it is trained from scratch in Europe, and its open weights are due at the end of October 2026. It isn't the smartest model available. What makes it notable is that it leads in a few areas where closed flagships either refuse or fall behind: defensive security work, locating objects in images, and legal research agents. Mistral released it on October 6, 2026 as a public preview. Its nickname is "Le Chonk". This

  October 9, 20266 min readNews
• 

  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 Pricing: The 100K Line Behind the 90% Cut

  Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens, a tenth of Haiku 4.5's $1 and $5. That holds for prompts up to 100,000 tokens. Above that line, the whole request is billed at $0.50 and $2.50, which is half of Haiku 4.5's price rather than a tenth. Anthropic puts the typical saving at around 75%, not 90%, and the difference comes from three things this post works through: where your prompts fall relative to the 100K line, how many thinking tokens the d

  October 8, 20268 min readOpinion
• 

  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
• 

  Claude Haiku 5.5 vs Haiku 4.5: What Ten Cents Now Buys

  Claude Haiku 4.5 scored 0.0% on Terminal-Bench 4.0. Claude Haiku 5.5 scores 39.2%, and it costs a tenth as much per token: $0.10 per million input tokens and $0.50 per million output tokens, against $1 and $5 for Haiku 4.5. That is the upgrade in one line. The small Claude model went from "fine for classification, not for agents" to a usable subagent, and its price now matches OpenAI's GPT-6 Luna to the cent. Anthropic released it on October 7, 2026 as Claude Haiku 5.5, model ID claude-haiku-5

  October 8, 20268 min readNews
• 

  Page Assist in Practice: Four Everyday Browser Workflows with Local and Cloud Models

  Most AI chat tools live in their own tab. You copy text out of a page, paste it into a chat window, and copy the answer back. Page Assist removes that round trip: it is an open-source browser extension that opens a model in a sidebar next to whatever page you are reading, plus a full-tab web UI for longer conversations. It started as a front end for local models running in Ollama, and that is still the default. But it also accepts any OpenAI-compatible endpoint, which means the same sidebar can

  October 8, 20269 min readTutorial
• 

  Migrating to GPT-6.1 Sol: 9 Things That Can Go Wrong

  Moving from GPT-6 Sol to 6.1 Sol looks like a one-line change, and the price is the same. But there are a few breaking changes and some shifts in behavior, so changing only the model name can get you errors, a surprise bill, or an agent that behaves differently. OpenAI's GPT-6 migration guide covers most of the official changes. This post adds the things that tend to bite in practice. They're ordered from "fails loudly" to "fails quietly." 1. reasoning_effort: "none" returns a 400 What you'l

  September 30, 20268 min readTutorial
• 

  What GPT-6.1 Sol Really Costs: Beyond the $2 / $10 Price Tag

  GPT-6.1 Sol has the same list price as GPT-6 Sol: $2 per million input tokens and $10 per million output tokens. Your actual bill depends on four other things: how often you hit the cache, whether you cross 272K input tokens, which service tier you use, and how many reasoning tokens the model burns. This post goes through each one. The full price list Standard rates (per 1M tokens) GPT-6.1 SolGPT-6 SolGPT-6 AstraGPT-6 LunaInput$2.00$2.00$10.00$0.10Cached input$0.10$0.20$1.00—Cache writes$

  September 30, 20266 min readOpinion