Spiral gives your agent every tool with one account. Browse the tools →

AlexandriaFinanceAvailable now

FRED · Series search

fred/series/search

Get market and financial data with FRED · Series search from Alexandria through one Spiral API key. The way in when all you have is words. Set search_type to series_id when the query is an id fragment rather than a description; the default full-text mode stems, so UNRATE under it matches on unrelated titles. It runs in the background and returns structured JSON. Pay as you go, with no subscription.

Pricing

$0.013 per call.

Limits

Runs
In the background
Returns
json
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

FieldKindDefaultDescription
search_text requiredtext—

The words to match against series.

limitnumber
… to 1000
1000

Records to return. The default is the maximum, so a naive call is a large response rather than a page.

offsetnumber0

Records to skip. Page by adding limit to it; count in the envelope is the full match total.

order_byone of
search_rank, series_id, title, units, frequency, seasonal_adjustment, realtime_start, realtime_end, last_updated, observation_start, observation_end, popularity, group_popularity
—

Which attribute to sort by. The default is conditional and cannot be stated here: search_rank when search_type is full_text, series_id when it is series_id.

tag_namestext—

Semicolon-delimited tag names a series must carry all of, for example usa;m2.

sort_orderone of
asc, desc
—

Sort direction. Also conditional: FRED defaults to desc when order_by is search_rank or popularity, asc otherwise.

search_typeone of
full_text, series_id
full_text

full_text stems the words across title, units, frequency and tags. series_id is a substring match on ids with * as a wildcard, which is what a ticker-shaped query wants - passing one under the default gets stem-matched noise instead.

filter_valuetext—

The value filter_variable must take. Inert on its own.

realtime_endtext—

End of the real-time period, YYYY-MM-DD. Defaults to today. Set 9999-12-31 for the full revision history.

realtime_starttext—

Start of the real-time period, YYYY-MM-DD. Defaults to today, which means the current vintage only. Set 1776-07-04 for the full revision history. Setting one bound implies the other.

filter_variableone of
frequency, units, seasonal_adjustment
—

Which series attribute to filter on. Inert without filter_value.

exclude_tag_namestext—

Semicolon-delimited tag names to drop. Not independently usable: FRED requires tag_names to be set as well, which nothing in this contract can enforce.

Same request in code

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": "fred/series/search",
    "input": {
      "search_text": "<search_text>"
    }
  }'

Frequently asked questions

How much does FRED · Series search cost?

$0.013 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 FRED · Series search through an API?

Send `POST /v1/runs` with `"provider": "alexandria"`, `"model": "fred/series/search"` 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 FRED · Series search?

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

Can my AI agent use FRED · Series search?

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