CrawlForge
Api Reference
...
Tools
List Ollama Models
AI ToolFree

list_ollama_models

A free discovery helper that lists models available on a local Ollama instance. Use it to find out which models you can pass to extract_with_llm for private, on-device LLM extraction. Zero credits per call.

Use Cases

Discover Available Models

List every model pulled into your local Ollama instance before kicking off extraction jobs.

Verify Ollama Setup

Quickly confirm that your Ollama server is reachable and serving the models you expect.

Pair with extract_with_llm

Programmatically pick a model name from this list and pass it straight to extract_with_llm.

Endpoint

POST/api/v1/tools/list_ollama_models
Auth Required
2 req/s on Free plan
0 credits

Parameters

NameTypeRequiredDefaultDescription
baseUrl
stringOptionalhttp://localhost:11434
Base URL of the local Ollama instance to query
Example: http://localhost:11434
Local-only: This tool queries an Ollama instance reachable from the calling environment. The default http://localhost:11434 only resolves when Ollama is running on the same machine as your MCP client.

Request Examples

cURL

terminalBash

TypeScript

listOllamaModels.tsTypescript

Response Example

200 OK0.2s
{
"success": true,
"data": {
"base_url": "http://localhost:11434",
"count": 3,
"models": [
{
"name": "llama3.1:8b",
"size": 4700000000,
"modified_at": "2026-04-20T10:00:00Z",
"digest": "sha256:abc123..."
},
{
"name": "qwen2.5:7b",
"size": 4400000000,
"modified_at": "2026-04-15T08:30:00Z",
"digest": "sha256:def456..."
},
{
"name": "mistral:7b",
"size": 4100000000,
"modified_at": "2026-03-30T12:15:00Z",
"digest": "sha256:123456..."
}
]
},
"credits_used": 0,
"credits_remaining": 1000,
"processing_time": 215
}
Field Descriptions
data.base_urlOllama instance that was queried
data.countNumber of models returned
data.modelsArray of installed models with name, size (bytes), modified_at, and digest
credits_usedAlways 0 — this tool is free

Credit Cost

Free
0 credits per call
Free — 0 credits per call. Use it freely for discovery.

Tip: Cache the response client-side if you call this on every extraction — the model list rarely changes between requests.

Related Tools

extract_with_llm
LLM-powered extraction — pass a model name discovered here
Ready to run local LLM extraction? Sign up for free and get 1,000 credits.