Provided by Exa
Get the Body Text of Several Pages From Their URLs (Exa)
Get the body text of up to 10 documents from the urls already in hand: each delivered page comes back with its title, author, published date and its text, with an optional cap on characters. A URL that cannot be retrieved is reported on its own and is not charged. It reads the urls supplied to it — it does not find them.
How to run it
Step 1Set up
Once: paste this into your agent's chat. The Skill installs the CLI and logs in by itself. For an agent that cannot use a shell, connect it over MCP instead.
set up https://glasser.ai/SKILL.md
Show me how to use the Exa endpoint /contents on Glasser.glasser run -p exa -e '/contents' -i '{"urls":["https://en.wikipedia.org/wiki/Battery_recycling"],"maxCharacters":2000}' --endpoint-version 1Uses endpoint version 1. Inspect the current price before running. Install and log in first on Get Started.
Once per Run:
IDEMPOTENCY_KEY=$(uuidgen)Run it, and copy this same block to send it again:
curl -X POST https://api.glasser.ai/v1/runs \
-H "Authorization: Bearer gl_..." \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-H "Content-Type: application/json" \
-d '{"provider":"exa","endpoint":"/contents","input":{"urls":["https://en.wikipedia.org/wiki/Battery_recycling"],"maxCharacters":2000},"endpoint_version":1}'Reuse the same Idempotency-Key to send it again: the second send is a read of the first Run. A new key is a new Run and a new Charge. Uses endpoint version 1; inspect the current price before running.
Step 2Try a specific example task
When you need to answer a research question from a particular webpage, you might collect relevant passages to support your notes.
Copy this prompt into your agent to find passages relevant to your research question.
Use exa:/contents on Glasser.
Read my source page and pull passages that answer the research question I provide.Endpoint structure
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"urls"
],
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string",
"pattern": "^https?:\\/\\/",
"maxLength": 2048,
"minLength": 8
},
"maxItems": 10,
"minItems": 1
},
"maxAgeHours": {
"type": "integer",
"maximum": 720,
"minimum": -1
},
"maxCharacters": {
"type": "integer",
"maximum": 10000,
"minimum": 1
},
"livecrawlTimeout": {
"type": "integer",
"maximum": 12000,
"minimum": 1000
}
},
"additionalProperties": false
}{
"urls": [
"https://en.wikipedia.org/wiki/Battery_recycling"
],
"maxCharacters": 2000
}This Endpoint publishes no output schema. You get the Provider's own response body, unchanged — we do not warrant a shape we cannot guarantee.
How pricing works
| Per result returned | Charged for each result returned. No charge when no data is returned. | $0.0011 |
|---|---|---|
| Maximum per Run | The total charge will not exceed this amount. | $0.05 |
| Provider error | The Provider failed to answer. | $0.00 |
| Timed out | The Run exceeded its time limit. | $0.00 |
| Internal failure | An internal error prevented completion. | $0.00 |