Provided by Exa
Answer One Question From Web Sources, With Citations (Exa)
Answer one natural-language question from Exa's page index: Exa retrieves the relevant pages first, then returns a direct written answer together with the source pages it cited, each with title, link, published date and author. One question per request, not a batch of questions, and the citations come back with the answer — it is grounded in retrieved pages rather than in a model's memory.
Contract snapshot: 2026-09-17. Inspect in Glasser for current terms.
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"text": {
"type": "boolean"
},
"query": {
"type": "string",
"maxLength": 2000,
"minLength": 1
},
"outputSchema": {
"type": "object",
"required": [
"type",
"properties"
],
"properties": {
"type": {
"anyOf": [
{
"enum": [
"object"
],
"type": "string"
}
]
},
"required": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[A-Za-z_][A-Za-z0-9_]*$",
"maxLength": 64,
"minLength": 1
},
"maxItems": 20,
"minItems": 1
},
"properties": {
"type": "object",
"patternProperties": {
"^[A-Za-z_][A-Za-z0-9_]*$": {
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"string",
"number",
"integer",
"boolean"
],
"type": "string"
},
"description": {
"type": "string",
"maxLength": 300,
"minLength": 1
}
},
"additionalProperties": false
}
}
}
},
"additionalProperties": false
}
},
"additionalProperties": false
}{
"query": "What is the latest valuation of SpaceX?"
}This Endpoint publishes no output schema. You get the Provider's own response body, unchanged — we do not warrant a shape we cannot guarantee.
How to run it
Two fields identify it: the Provider and the endpoint key. The key looks like a path because it usually mirrors the Provider's own, but it is an opaque identifier — not a URL you can open. The same provider:endpoint pair is what your Policy lists.
Once: paste this into your agent's chat. The Skill installs the CLI and logs in by itself. For an agent that cannot use a shell, connect it over MCP instead.
set up https://glasser.ai/SKILL.mdThen ask for this Endpoint:
Run the Exa Endpoint /answer on Glasser with input {"query":"What is the latest valuation of SpaceX?"}glasser run -p exa -e '/answer' -i '{"query":"What is the latest valuation of SpaceX?"}' --endpoint-version 1Pinned to version 1, the one this page shows: if a newer version is published first, the Run is refused instead of charged under new terms. Install and log in first on Get Started.
Once per Run:
IDEMPOTENCY_KEY=$(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":"/answer","input":{"query":"What is the latest valuation of SpaceX?"},"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. Pinned to version 1 for the same reason as the CLI.
What each outcome charges
| No result | The Provider answered: nothing matched. | $0.00 |
|---|---|---|
| Provider error | The Provider failed to answer. | $0.00 |
| Timed out | The deadline won. | $0.00 |
| Internal failure | Our defect. | $0.00 |