update-models-xai

update-models-xai is a command for Claude Code from enricoros/big-AGI. It costs 10 tokens per session (681 once invoked), scanned A, original, MIT.

A command that updates the code’s definitions of xAI’s language models, including their latest prices and documented capabilities.

In plain words
What is it for?
Use it when xAI adds or changes models, pricing, supported inputs, capabilities, or reasoning-effort options.
Why use it?
It helps keep the application’s model list aligned with the provider’s current documentation and API behavior, including settings that documentation may omit.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it when xAI adds or changes models, pricing, supported inputs, capabilities, or reasoning-effort options.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/enricoros/big-agi/update-models-xai
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-xai

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/enricoros/big-agi/update-models-xai"><img src="https://agentmods.dev/badge/commands/enricoros/big-agi/update-models-xai.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 681 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00681
Opus 5 $0.00005 $0.00341
Sonnet 5 $0.00002 $0.00136
Haiku 4.5 $0.00001 $0.00068

Measured 10d ago against content hash 81bc92167c0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

update-models-xai scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Known Issue:** `curl` on docs.x.ai returns 521; WebFetch works. x.ai/news/* still 403s - use fallbacks below for release dates.
.claude/commands/llms/update-models-xai.md · 27 lines

What it actually says

Update src/modules/llms/server/openai/models/xai.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:

  • Models & Pricing: https://docs.x.ai/developers/models (canonical since ~2026; /docs/models still resolves). Two kinds of per-model pages: detail/pricing pages at /developers/models/<dotted-id> (e.g. /developers/models/grok-4.3) exist for every served model and carry context/pricing tiers/modalities/capability flags; hand-written guides at /developers/<dashed-id> (e.g. /developers/grok-4-5) exist for only a few models (grok-4-3, grok-build-0-1 404) and are the only place with knowledge cutoffs. /developers/changelog 404s; /developers/release-notes exists but was stale (no 2026 entries) as of 2026-08.
  • Docs' effort lists are incomplete: they omitted xhigh for grok-4.5 while the API accepts it. Always probe efforts rather than trusting the table.
  • Note: docs/press now brand the vendor "SpaceXAI" (post-merger); model ids and the xai owned_by are unchanged.

Known Issue: curl on docs.x.ai returns 521; WebFetch works. x.ai/news/* still 403s - use fallbacks below for release dates.

Fallbacks if blocked:

Live endpoint (extra signal): If .env.api-keys has XAI_API_KEY, scan the served model list as ground-truth for what's new/available and cross-check the docs above. Fetch BOTH, they are complementary: /v1/models is the only source of context_length (and lists the non-chat imagine models), /v1/language-models is the only source of input_modalities/output_modalities/fingerprint and is what the app actually calls; pricing/aliases/long-context tiers appear in both. curl https://api.x.ai/v1/models -H "Authorization: Bearer $XAI_API_KEY". Never commit or echo the key.

Important:

  • Review the full model list for additions, removals, and price changes
  • 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 · 27 lines · 10 tokens per session scan A 81bc92167c0e

Subscribe to this mod's changes

update-models-xai 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 681 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.