models

A command for listing the embedding models available for vector search, which finds related content by comparing numeric representations of text or code. It shows each model's name, vector size, backend, intended use, and model identifier.

In plain words
What is it for?
Use it to inspect available models with `/models list` or get machine-readable results with `/models list --json`.
Why use it?
It lets you see which models are available before choosing one for documents, PDFs, or source code. JSON output is available for scripts and other tools.

Command

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.

agentmods
npx agentmods add commands/cwensel/arcaneum/models
Clone the repo
git clone --depth 1 https://github.com/cwensel/arcaneum
Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 938 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00003 $0.00938
Opus 5 $0.00002 $0.00469
Sonnet 5 $0.00001 $0.00188
Haiku 4.5 $0.00000 $0.00094

Measured 2d ago against content hash 94df3c72e3d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

models 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 2d 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.

commands/models.md · 113 lines

What it actually says

Manage and view available embedding models for vector search.

IMPORTANT: You must specify a subcommand (currently only list is available).

Subcommands (required):

  • list: List all available embedding models with details

Options:

  • --json: Output in JSON format

Examples:

/models list
/models list --json

Execution:

arc models $ARGUMENTS

Available Models:

The list command shows:

  • Model name (for --model flags)
  • Dimensions (vector size)
  • Backend (fastembed, sentence-transformers)
  • Best use case (PDFs, code, general)
  • Model ID (HuggingFace identifier)

Current Models:

For Documents/PDFs:

  • arctic-m (768D): DEFAULT - stable FastEmbed retrieval model
  • stella (1024D): Highest-quality opt-in document model, requires arcaneum[sentence-transformers]
  • mxbai-large (1024D): High-quality FastEmbed document model
  • bge-large (1024D): Legacy BGE document model

For Source Code:

  • jina-code (768D): DEFAULT - stable FastEmbed code model
  • jina-code-st (768D): Legacy SentenceTransformers code path, requires arcaneum[sentence-transformers]
  • jina-code-0.5b (896D): Higher-quality opt-in code model, 32K context, requires arcaneum[sentence-transformers]
  • jina-code-1.5b (1536D): SOTA Sept 2025, 32K context, highest quality, requires arcaneum[sentence-transformers]
  • codesage-large (1024D): CodeSage V2, Dec 2024, 9 languages, requires arcaneum[sentence-transformers]
  • nomic-code (3584D): 7B params, 6 languages, slower but comprehensive, requires arcaneum[sentence-transformers]

For General Use:

  • bge (1024D): High-quality general embeddings
  • bge-small (384D): Faster, smaller, lower quality

Model Selection Tips:

  1. Match content type:

    • PDFs/docs → arctic-m (stable default), stella (quality), or mxbai-large (FastEmbed quality)
    • Source code → jina-code (stable FastEmbed default), jina-code-0.5b or jina-code-1.5b (quality extra)
    • Mixed → arctic-m or mxbai-large
  2. Consider dimensions:

    • Higher dimensions (1024D) = better quality, more storage
    • Lower dimensions (384D, 768D) = faster, less storage
  3. Backend matters:

    • fastembed: Faster, optimized, limited models
    • sentence-transformers: More models, HuggingFace ecosystem
  4. Collection consistency:

    • Use same model for all documents in a collection
    • Cannot mix dimensions in one vector space

Downloading Models:

Models auto-download on first use. FastEmbed defaults are part of the core install; SentenceTransformers models require arcaneum[sentence-transformers].

  • Cached in ~/.cache/arcaneum/models (XDG-compliant)
  • Reused across indexing operations
  • Use --offline flag to require cached models

Pre-download for offline use:

# Download an opt-in higher-quality code model
python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('jinaai/jina-code-embeddings-0.5b')"

# Or the legacy v2 SentenceTransformers model
python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('jinaai/jina-embeddings-v2-base-code')"

Related Commands:

  • /collection create - Create collection with specific model
  • /index pdf - Index with model selection
  • /index code - Index with model selection

Implementation:

  • RDR-002: Embedding client architecture
  • RDR-006: Model listing CLI
  • arcaneum-142: Multi-backend support
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. 2d ago First seen · 113 lines · 3 tokens per session scan A 94df3c72e3d4

Subscribe to this mod's changes

models is a command published in the GitHub repository cwensel/arcaneum (7 stars, last pushed 6d ago), licensed MIT. It adds 3 tokens to every session and 938 once invoked, about $0.0000 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 2026-08-31.