update-models-minimax

update-models-minimax is a command for Claude Code from enricoros/big-AGI. It costs 10 tokens per session (761 once invoked), scanned A, original, MIT.

A command for updating the list of MiniMax language models in a codebase, along with their pricing limits and supported capabilities. MiniMax is an AI model provider with an OpenAI-compatible API.

In plain words
What is it for?
Use it to revise the MiniMax model-definition file using the provider's release notes, pricing pages, and API reference while leaving unrelated code untouched.
Why use it?
It keeps hardcoded model definitions aligned with the provider's current documentation, including context sizes, output limits, pricing, and API options.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it to revise the MiniMax model-definition file using the provider's release notes, pricing pages, and API reference while leaving unrelated code untouched.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/enricoros/big-agi/update-models-minimax
About the project

Big-AGI is an open-source workspace for using multiple AI models through chat and other AI functions. It is intended for engineers, founders, researchers, and other users who want to work with AI personas, model comparisons, image generation, voice, documents, and code-related features. The catalogue entries provide commands, instructions, and a skill for working with Big-AGI.

enricoros/big-AGI · 7,118 stars · on GitHub · big-agi.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/enricoros/big-AGI

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for update-models-minimax

README.md
[![agentmods](https://agentmods.dev/badge/commands/enricoros/big-agi/update-models-minimax/github.svg)](https://agentmods.dev/commands/enricoros/big-agi/update-models-minimax)
Your own site
<a href="https://agentmods.dev/commands/enricoros/big-agi/update-models-minimax"><img src="https://agentmods.dev/badge/commands/enricoros/big-agi/update-models-minimax/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for update-models-minimax

Your own site · 80×15
<a href="https://agentmods.dev/commands/enricoros/big-agi/update-models-minimax"><img src="https://agentmods.dev/badge/commands/enricoros/big-agi/update-models-minimax.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 761 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00010 $0.00761
Opus 5 $0.00005 $0.00380
Sonnet 5 $0.00002 $0.00152
Haiku 4.5 $0.00001 $0.00076

Measured 10d ago against content hash 3aa74a835da4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

update-models-minimax scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/llms/update-models-minimax.md · 35 lines

What it actually says

Update src/modules/llms/server/openai/models/minimax.models.ts with latest model definitions.

Reference src/modules/llms/server/llm.server.types.ts and src/modules/llms/server/models.mappings.ts for context only. Focus on the model file, do not descend into other code.

Primary Sources:

Note: MiniMax stays hardcoded: GET https://api.minimax.io/v1/models exists but returns bare {id, created, owned_by} (no context/pricing/capabilities) and omits still-served legacy ids. Context windows, max output, and pricing must be maintained from the docs. Pay attention to new model releases (M-series), highspeed variants, and deprecated models.

Fallbacks if blocked: Search "minimax api models pricing", "minimax m2 m3 models", "minimax api changelog" or check https://openrouter.ai models list for MiniMax entries.

Live probes (ground truth, needs MINIMAX_API_KEY from .env.api-keys, never echo it):

  • GET /v1/models for the served-and-supported set (its created is the vendor release date, often +1 day vs the release notes - keep the file's doc-derived pubDate)
  • A 1-token POST /v1/chat/completions confirms unlisted/legacy ids are still served (400 unknown model = dead). Careful: not every served id carries the MiniMax- prefix (e.g. M2-her), and MiniMax-01 is dead while MiniMax-Text-01 is live
  • An over-large max_completion_tokens 400s with the exact per-model ceiling in the message (M3 524288, M2.x/M1 196608, Text-01 40000, M2-her 2048) - cheapest way to check max output
  • Tool support: send tools + tool_choice: 'required'; M2-her silently ignores both (no function calling)
  • Vision: an image_url part never 400s, so absence of an error proves nothing - compare usage.prompt_tokens with vs without the image (M3 grows, M2.x is identical = image silently dropped)

Important:

  • Models are ModelDescriptionSchema[] objects (not ManualMappings) - match existing pattern in the file
  • Review the full model list for additions, removals, and price changes
  • Check for new -highspeed variants and new model families
  • Verify context window sizes and max completion tokens against docs
  • Minimize whitespace/comment changes, focus on content
  • Preserve comments to make diffs easy to review
  • Flag broken links or unexpected content
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 35 lines · 10 tokens per session scan A 3aa74a835da4

Subscribe to this mod's changes

update-models-minimax is a command published in the GitHub repository enricoros/big-AGI (7,118 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 761 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.