# Ollama model library · Layer metadata

Get developer and code data with Ollama model library · Layer metadata from Alexandria through one Spiral API key. Compare embedding models on true context length and vector dimension, or inspect quantisation per tensor; the `layer_digest` is a model layer's `short_digest` from tag. It runs in the background and returns structured JSON. Pay as you go, with no subscription.

- Provider: Alexandria
- Category: Developer
- Runs: In the background
- Returns: json
- Tool id: `alexandria` / `ollama-com/models/layer_metadata`
- Page: https://spiral.ai/tools/alexandria/ollama-com/models/layer_metadata

## Pricing

$0.00873 per call.

## Limits

- Longest queue wait: 1 hour
- Run deadline: 5 minutes
- Longest run, end to end: 225 minutes
- Largest inline input: 1 MB
- Largest input file: 2 GB
- Largest output: 5 GB

## Input

| Field | Kind | Allowed | Default | Description |
| --- | --- | --- | --- | --- |
| `tag` (required) | text |  | — | Tag after the colon, e.g. `latest`, `0.6b`, `137m-v1.5-fp16`. Pattern: ^[A-Za-z0-9._-]+$. |
| `model` (required) | text |  | — | Model name as on ollama.com: `nomic-embed-text` (official, namespace `library`) or `namespace/name` for a community model (e.g. `aiconjured/embeddinggemma-300M-NVFP4-Q8-GGUF`). No `:tag`. Pattern: ^[A-Za-z0-9._-]+(/[A-Za-z0-9._-]+)?$. |
| `layer_digest` (required) | text |  | — | 12-hex short digest from tag.layers[].short_digest (a full sha256 is accepted and shortened). Pattern: ^(sha256:)?[0-9a-fA-F]{12}([0-9a-fA-F]{52})?$. |
| `include_tensors` | true or false |  | — | Return the tensor table (name, type, shape); a few hundred rows. Default false. |

## Example

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "alexandria",
    "model": "ollama-com/models/layer_metadata",
    "input": {
      "tag": "<tag>",
      "model": "<model>",
      "layer_digest": "<layer_digest>"
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=alexandria&model=ollama-com%2Fmodels%2Flayer_metadata

## Common questions

### Ollama model library · Layer metadata

**How much does Ollama model library · Layer metadata cost?**

$0.00873 per call. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use Ollama model library · Layer metadata through an API?**

Send `POST /v1/runs` with `"provider": "alexandria"`, `"model": "ollama-com/models/layer_metadata"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

**Do I need an account with Alexandria to use Ollama model library · Layer metadata?**

No. Spiral runs it on its own Alexandria account and charges your Spiral balance.

**Can my AI agent use Ollama model library · Layer metadata?**

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.

