{"slug": "running-mistral-large-4-mistral-large-4-0-on-stock-mistral-vibe-config-only-no", "title": "Running Mistral Large 4 (mistral-large-4-0) on stock Mistral Vibe — config-only, no fork", "summary": "A developer documented a configuration-only method for running Mistral Large 4 (mistral-large-4-0) in the stock Mistral Vibe CLI (v2.26.0) without forking the repository. By adding a [[models]] TOML block to ~/.vibe/config.toml, the model union-merges with Vibe's built-in catalog by alias, using the existing mistral provider and MISTRAL_API_KEY; a separate agent profile in ~/.vibe/agents/ can pin the model. The writeup notes launch pricing of $0.68 per million input tokens, $0.07 cached input and $2.09 output, a 1M-token context with a 900k auto-compaction threshold, and that thinking mode is set per-model rather than at the top level.", "body_md": "*Tested on Mistral Vibe **v2.26.0** using `vibe --yolo --experimental-harness`. Everything below uses the documented configuration surface (the same one the CLI's built-in `/config` browser and skill docs describe), so it should keep working on later releases — no patching, no rebase pain.*\n\nMistral Large 4 (`mistral-large-4-0`, public preview, released 6 October 2026) is served on the Mistral API — but if you fire up Mistral Vibe and hit `/model`, it's not in the picker. The CLI ships a small, curated default model catalog, and Large 4 simply isn't in it yet.\n\nThe tempting move is to fork the repo and append the model to the hardcoded `DEFAULT_MODELS` list. Don't. You don't need any custom code: Vibe's configuration is layered, the `models` list **union-merges with the built-ins by alias**, and the stock `mistral` provider already points at `https://api.mistral.ai/v1` using `MISTRAL_API_KEY` — which is exactly where Large 4 is served. You're one TOML block away.\n\nOpen (or create) `~/.vibe/config.toml` and add:\n\n```\n[[models]]\nname = \"mistral-large-4-0\"\nprovider = \"mistral\"\nalias = \"mistral-large-4\"\ntemperature = 0.2\ninput_price = 0.68\noutput_price = 2.09\ncached_input_price = 0.07\nthinking = \"medium\"\nsupports_images = true\nauto_compact_threshold = 900000\n```\n\nThen `/reload` and pick `mistral-large-4` in `/model`. To boot straight onto it, set at the top of the config:\n\n```\nactive_model = \"mistral-large-4\"\n```\n\nStraight off the [model card](https://docs.mistral.ai/models/mistral-large-4-0):\n\n- **Prices** are the launch sale prices per million tokens: $0.68 input, $0.07 cached input, $2.09 output (list prices are $1.36 / $0.14 / $4.18). If the sale ends, bump the three price fields.\n- **Context** is 1M tokens, hence the 900k auto-compaction threshold.\n- **`supports_images = true`** : Large 4 is natively multimodal (1.6B vision encoder), so`@` -mentioned images work.\n- **`thinking = \"medium\"`** : Large 4 is a hybrid instruct-and-reasoning model. If the preview API rejects the thinking parameter, set`thinking = \"off\"` — that's the one field to watch on a preview model.\n- **`temperature = 0.2`** matches the coding-agent default used for other hand-added models; adjust to taste.\n\nVibe's agents (cycle them with `Shift+Tab`) aren't just permission presets — they're **config profiles**, and a profile can pin a model. Any `*.toml` dropped into `~/.vibe/agents/` is discovered automatically. For a dedicated Large 4 agent, create `~/.vibe/agents/large4.toml`:\n\n```\ndescription = \"Mistral Large 4 via the Mistral API\"\nactive_model = \"mistral-large-4\"\n```\n\nNow `Shift+Tab` onto it (or launch with `--agent large4`).\n\nNote: if you use the flag `vibe --experimental-harness` then the opensource python vibe harness will load the new rust engine to be faster, more efficient, and more secure. Joy.\n\n- **Back up first.**`cp ~/.vibe/config.toml ~/.vibe/config.toml.bak` before editing — the config is hand-edited TOML, and a syntax slip takes the whole file down.\n- **Agents can hijack your model.** Any agent profile with an`active_model` line switches the model the instant you cycle onto it. Grep custom agents for`active_model` if you get mysteriously moved off Large 4.\n- **There is no top-level `thinking` config field.** Thinking mode lives*inside* each`[[models]]` entry. A`thinking = \"medium\"` line sitting loose in an agent TOML does nothing at all.\n- **The \"Default\" row in `/model` means \"unpin\".** Selecting it reverts to the default model. Pick your model explicitly.\n- **Picker selections persist.** Choosing a model in`/model` writes`active_model` back to`~/.vibe/config.toml` , so your choice survives restarts.\n- **It's a public preview.** The model ID, pricing, and thinking support can move under you; re-check the model card after Mistral ships the weights (due end of October 2026).\n- **Per-project configs work too.** The same`[[models]]` block can live in a repo's`.vibe/config.toml` — handy when you only want Large 4 for one codebase.\n\nZero code changes. The union-merge means your `[[models]]` entry rides alongside the built-ins (and if upstream ever ships Large 4 in the default catalog, your entry just overrides it by alias — same values, no duplicates, no conflict). Every `uv` update, every new Vibe release, your config keeps working untouched.\n\n```\nvibe --version                                     # the CLI version you launched\ngrep -A11 'mistral-large-4-0' ~/.vibe/config.toml  # the block, as written\nuv tool list | grep vibe                           # the uv tool install version\n```\n\nIn-session, the startup banner shows the active model (`mistral-large-4[medium]`), and `/model` lists `mistral-large-4` in the picker. If `vibe --version` prints something older than expected, your PATH is resolving a second, older install — check `which vibe`.", "url": "https://wpnews.pro/news/running-mistral-large-4-mistral-large-4-0-on-stock-mistral-vibe-config-only-no", "canonical_source": "https://gist.github.com/simbo1905/6f46cc1209ce57d9a775797ad870874b", "published_at": "2026-10-07 22:13:53+00:00", "updated_at": "2026-10-18 23:50:25.456809+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "developer-tools", "ai-agents"], "entities": ["Mistral", "Mistral Large 4", "Mistral Vibe", "mistral-large-4-0"], "also_reported_by": [], "takeaway": "Adding a [[models]] block with alias \"mistral-large-4\" to ~/.vibe/config.toml union-merges Mistral Large 4 into stock Vibe's catalog without a fork, with launch pricing of $0.68/$0.07/$2.09 per million input/cached/output tokens and a 900k auto-compaction threshold for the 1M-token context.", "recommendation": null, "alternates": {"html": "https://wpnews.pro/news/running-mistral-large-4-mistral-large-4-0-on-stock-mistral-vibe-config-only-no", "markdown": "https://wpnews.pro/news/running-mistral-large-4-mistral-large-4-0-on-stock-mistral-vibe-config-only-no.md", "text": "https://wpnews.pro/news/running-mistral-large-4-mistral-large-4-0-on-stock-mistral-vibe-config-only-no.txt", "jsonld": "https://wpnews.pro/news/running-mistral-large-4-mistral-large-4-0-on-stock-mistral-vibe-config-only-no.jsonld"}}