Tutorial
Tutorial posts from the AIHubMix team.
Nowdex: your AI subscription quotas, on the screen you're already holdingIf you pay for more than one coding agent, you already know the shape of the problem. Claude has a five-hour window and a weekly one. Codex has a weekly quota with reset credits, and a session window on some plans. Cursor counts usage and spend limits. Each of them reports on a different dashboard, each resets on its own schedule, and none of them is on the phone in your pocket. Nowdex is an app built around that gap. It collects the remaining usage and reset times of the services you already
Migrating to GPT-6.1 Terra: Fix the temperature 400s, Move Tools to Responses, and Set Up CodexSwitching to GPT-6.1 Terra is a one-line change: set the model to gpt-6.1-terra. What happens next depends on which API route the request takes. On the Responses API, Terra follows OpenAI's rules: reasoning effort works, and temperature or top_p return HTTP 400. On AIHubMix's Chat Completions route, the same temperature is accepted without complaint, and in AIHubMix's checks on 27 October 2026, reasoning_effort made no measurable difference on small prompts. So the short answer for most teams:
Migrating to Kimi K3.1 Pro: Fix the 400s, Mind the Max-Effort Default, and Don't Mistype HighspeedKimi K3.1 Pro is live in Kimi Code, on Moonshot's API as kimi-k3.1-pro, and on AIHubMix under the same ID. Moonshot gives it the same parameter constraints as Kimi K3, so code that already runs on K3 should move with a model-ID change and a fresh session. Code written for K2.x now has a deadline on Moonshot's platform: Moonshot closes the K2 series to newly registered users there on 31 October 2026 and plans to retire it by the end of December. That code is also the most likely to break, because
Claude Code settings.json and Environment Variables: Base URL, Auth Token and ModelClaude Code takes its configuration from JSON settings files and from environment variables. To run it through a gateway instead of Anthropic's API, you need two variables, ANTHROPIC_BASE_URL and a token, and usually a model. The variables are simple. What confuses people is where to put them, because the same variable can sit in your shell profile, in several settings.json files and in VS Code's settings. This guide starts with a setup that works, then explains where the files live, which val
MiniMax M3.1 Flash Effort Levels: Why the Default Cost 7× Low on the Same Bug FixMiniMax M3.1 Flash has five thinking levels and no off switch. If you don't pick a level, the model picks the deepest one for you. MiniMax's text generation guide says effort "defaults to max when omitted." That default is expensive in a way that's easy to miss. AIHubMix ran the same two-bug fix at every level. The default used about 10× the thinking tokens of low and took about 6× as long, and every run at every level passed all 215 tests. The model's thinking cost rose with the effort settin
Moving Off MiniMax M2.5/M2.7 Before Nov 18: Fixing M3.1 Flash's "requires adaptive thinking" 400MiniMax is retiring M2.5 and M2.7 on 18 November 2026, and the switch has already started. Since 19 October, the two older families have been closed to new users, and plan requests that name them are served by M3.1 Flash. If you're on pay-as-you-go, you have four weeks to change the model ID yourself. Most M2.7 code runs on M3.1 Flash unchanged. The trouble comes from one design choice: M3.1 Flash always thinks, and it thinks at the deepest level unless you say otherwise. That produces one lou
How to Set Up Codex config.toml: Custom API, Proxy, and Common ErrorsCodex keeps its settings in one file, config.toml: which model to use, which API to call, and how much the agent may do without asking. The format changed several times in 2026, and many guides from earlier in the year show settings that now stop Codex from starting. This guide gives you a working config first, then the parts most people change: profiles, project settings, the sandbox, and a proxy. At the end is a list of the errors you're likely to see, with what each one means. Checked again
Migrating to DeepSeek V4.1 Flash 1017: The reasoning_content 400, the Silent Alias Swap, and Peak-Hour BillingMost migrations start with changing a model name. DeepSeek V4.1 Flash 1017 did it the other way round: on October 17, 2026, DeepSeek kept the name deepseek-flash and changed the model behind it. Anyone calling deepseek-flash, deepseek-v4-flash, or deepseek-v4-flash-vision-exp on DeepSeek's API was moved over without touching a line of code. On AIHubMix the new checkpoint has its own ID, deepseek-v4.1-flash-1017, so you choose when to move. Either way, these are the problems to check: Prob
Qwen3.8 Free on AIHubMix: Fix 429s, "Rate Limited by Provider", and a Drained Token PoolUpdate (October 27, 2026): The free campaign has ended. GMI Cloud's campaign credits ran out before the planned end around November 13, and qwen3.8-max-free and qwen3.8-flash-free now return 404 model_retired. To keep using Qwen3.8, drop -free from the model ID and call the paid qwen3.8-max or qwen3.8-flash. Most problems with qwen3.8-max-free and qwen3.8-flash-free come from three places: the free-tier caps, the campaign capacity GMI Cloud has set aside upstream, and how quickly thinking toke
x402 Tutorial: Let Your AI Agent Top Up AIHubMix with USDCAIHubMix now accepts USDC top-ups. Your AI agent can add credit to its own account with the USDC in its wallet: no web page to open, and no one has to click a button. With x402, a top-up can be as small as $1. The agent tops up as it goes, so you don't have to load a large balance in advance. It takes two steps: get a token, a wallet, and some USDC ready on the web and in an app, then run our ready-made top-up script with one command. About 20 seconds after payment, the credit shows up in yo