--- title: "MiniMax in Claude Code — M3 for a whole team · Selan" description: "MiniMax runs in Claude Code through its Anthropic-format API. Run M3 for a team on OpenRouter or Ollama Cloud, beside Claude, no key on a laptop." url: https://selan.ai/guides/minimax-in-claude-code updated: 2026-11-09T09:52:52+02:00 --- Guide · Other models in Claude Code # How do you run MiniMax in Claude Code? Point Claude Code at `https://api.minimax.io/anthropic` with a MiniMax key, then name a MiniMax model. MiniMax's own guide uses MiniMax-M3.1-Flash in every model slot. Through Selan, an owner connects the company's OpenRouter key or Ollama Cloud plan once. Each developer then runs `selan claude --model openrouter:minimax/minimax-m3`. ## Why does MiniMax work in Claude Code at all? Claude Code sends every request in Anthropic's Messages format. It reaches another server when `ANTHROPIC_BASE_URL` is set to that server's address. MiniMax serves its models in that same format at `https://api.minimax.io/anthropic`. OpenRouter and Ollama's cloud answer in it too. So MiniMax needs no translation in the middle, unlike GPT. What it needs is the right key, the model names and the window. How GPT differs is in [running GPT in Claude Code](https://selan.ai/guides/gpt-in-claude-code). ## How do you set up MiniMax in Claude Code by hand? MiniMax's quickest way is its setup wizard. It installs Claude Code if it is missing and writes `~/.claude/settings.json`: ```bash npx -y mmx-cli@latest agent setup ``` By hand, MiniMax first has you unset `ANTHROPIC_AUTH_TOKEN` and `ANTHROPIC_BASE_URL`. Exported in a shell, they override the settings file. Then it puts these in the `env` block of `~/.claude/settings.json`: - `https://api.minimax.io/anthropic` as the base URL, and your M Plan API key as `ANTHROPIC_AUTH_TOKEN` - `MiniMax-M3.1-Flash[1m]` as the main model and as the Opus, Sonnet and Haiku models - `CLAUDE_CODE_AUTO_COMPACT_WINDOW` at `524288`, the 512K window MiniMax recommends - `CLAUDE_CODE_EFFORT_LEVEL` at `max` To check it, run `/status` and `/model` in a session. The base URL should read `api.minimax.io/anthropic`. Every request in that session then goes to MiniMax. Claude models are out of reach until you change the file back. That works for one person. On a team, it is one MiniMax key and one settings file per laptop. Why a key on every laptop is the expensive part is in [keeping API keys off laptops](https://selan.ai/guides/claude-code-without-api-keys). ## Which MiniMax key does Claude Code need? MiniMax has two kinds of key, and they cannot stand in for each other. | Key | What it spends | What it covers | | --- | --- | --- | | An M Plan API key | Your M Plan's included usage, then any credit packs you bought | MiniMax-M3.1-Flash on every tier (Go, Explore and Build) | | A pay-as-you-go API key | Your MiniMax account balance, per token | MiniMax-M3.1-Flash and MiniMax-M3 | A MiniMax account balance is charged only through a pay-as-you-go key. If a subscriber's balance still goes down, the tool is using the pay-as-you-go key. MiniMax's fix is to put the M Plan key there instead. An M Plan's text usage runs in a 5-hour window and a weekly window. Each starts with your first use and resets on its own. Explore gives three times Go's usage, and Build seven and a half times. Pay-as-you-go, MiniMax-M3.1-Flash costs $0.15 per million input tokens and $0.60 per million output tokens. MiniMax-M3 costs $0.30 and $1.20 up to 512K input tokens, and twice that above. ## Can a team share one MiniMax M Plan? No. MiniMax calls the M Plan its subscription for individuals. It is designed for one developer's interactive use, and MiniMax says to keep its key secure and not share it. One subscription can run in several tools at once, but every tool draws on the same usage limits. For production use, MiniMax recommends pay-as-you-go. A CI job belongs on a pay-as-you-go key, not on someone's M Plan. For one developer who wants only MiniMax, MiniMax's own setup on their own M Plan is the simpler answer. A gateway adds nothing there. ## How do you run MiniMax in Claude Code through Selan? Selan does not connect a MiniMax M Plan or a MiniMax key. It reaches MiniMax through an OpenRouter key or an Ollama Cloud plan, which an owner connects once. Developers install the `selan` CLI, sign in as themselves and name the model: ```bash selan claude --model openrouter:minimax/minimax-m3 ``` The part before the first colon is the provider. Everything after it is that provider's own model id, passed through as it is. So `openrouter:minimax/minimax-m3.1-flash` reaches M3.1 Flash the same way. MiniMax is not a model Selan lists, so nothing has to be added to Selan first. The model appears in Claude Code's `/model` picker for the session. The details are in [Run any model](https://selan.ai/docs#any-model). ## Which account does a MiniMax turn run on? | Route | How it bills | Name it as | | --- | --- | --- | | An OpenRouter key | Per token, on your OpenRouter invoice | `openrouter:minimax/minimax-m3` or `openrouter:minimax/minimax-m3.1-flash` | | An Ollama Cloud plan | Your Ollama plan's monthly usage, then any credits you bought | `ollama:minimax-m3` or `ollama:minimax-m2.7`, as Ollama lists them | A MiniMax turn runs on the provider its name points at, and on no other. If that account is out of quota, the request fails rather than moving to the other one. Selan lists MiniMax M3 on Ollama's cloud with a 1,000,000-token window, and M2.7 with 200,000. Ollama answers only when you name one of its models. A request that names no model never lands on it. How Ollama itself runs in Claude Code is in [using Ollama with Claude Code](https://selan.ai/guides/ollama-in-claude-code). All of this is on [Providers and models](https://selan.ai/docs/providers). When OpenRouter alone is the simpler answer is in [OpenRouter and Selan compared](https://selan.ai/compare/openrouter). ## What does a team get beyond the model? - **One usage record.** MiniMax turns land beside Claude turns, per person and per repository. [Usage per developer](https://selan.ai/guides/claude-code-usage-per-developer) shows what an owner sees. - **One spend limit.** An OpenRouter turn is metered, so it counts against a member's limit. A turn on an Ollama plan does not. See [spend limits](https://selan.ai/solutions/spend). - **No OpenRouter or Ollama key on a laptop.** Keys stay on the gateway. A developer holds a Selan session you can revoke. ## What should you check before switching a team to MiniMax? - **M3.1 Flash on Ollama.** Ollama's cloud listed `minimax-m3.1-flash` on 9 November 2026, but Selan's Ollama list did not yet include it. Through Selan, M3.1 Flash runs on OpenRouter. - **Thinking and spend.** MiniMax-M3.1-Flash always thinks, and a setting that turns thinking off has no effect on it. On OpenRouter, the thinking is metered too. - **The window.** MiniMax recommends a 512K window for everyday coding, even on a 1M model. In its own comparison, results were similar and the cost was about 20% lower. **Good to know:** Anthropic doesn't support routing Claude Code to non-Claude models through any gateway, Selan included. A MiniMax session is the gateway's to answer for, not Anthropic's. [Start for free](https://auth.selan.ai/r) Free for up to three seats, and the Free plan needs no card. ### The short version - MiniMax is served in Anthropic's API format, so Claude Code reaches it with no translation. - By hand, that is MiniMax's settings and a MiniMax key on every laptop, and an M Plan key and a pay-as-you-go key are not interchangeable. - An M Plan is one person's, for interactive use; MiniMax recommends pay-as-you-go for production. - Through Selan, a developer runs `selan claude --model openrouter:minimax/minimax-m3`, or `ollama:minimax-m3` on an Ollama Cloud plan. - MiniMax runs on your OpenRouter key or Ollama plan, with one usage record and no key on a laptop. The manual setup, the wizard and the thinking settings are MiniMax's Claude Code guide. The M Plan's tiers, windows, keys and usage rules are its M Plan introduction, FAQ and usage pages. The prices are its pricing overview and API reference. All were read on 9 November 2026, as were Ollama's cloud model list and OpenRouter's model list. Anthropic's position is its gateway docs, as read on 3 November 2026. What Selan does is its model list, its CLI and its providers and getting-started docs as they stood on 9 November 2026.