ai_text — Orange Slice capability

Outcome-priced capability. One price for the answer, whichever providers it took. Everything we expose, with prices: https://orangeslice.ai/llms.txt

Runs a prompt through a fast model and returns text. One credit per call, billed whether or not you like the answer — the model did the work either way. Use ai text_deep when the fast model is not good enough; it is the same call on a stronger model at ten credits.

Price

$0.002, charged per call

Billed on every call, including one that returns nothing.

The price is a property of the outcome, not of the work behind it. Whichever vendor serves this call, and whatever it costs us, the number above is the number quoted before the run and charged after it.

Call it

CLI

orangeslice ai text "Summarise this company in one line" --enable-web-search

# the usual shape: a typed capability produces evidence, this turns it into prose
orangeslice enrich scrape_website --url https://stripe.com \
  | orangeslice ai text "What does this company sell?"

HTTP

curl -X POST 'https://orangeslice.ai/api/v1/run' \
  -H 'Authorization: Bearer $ORANGESLICE_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"capability":"ai_text","input":{"prompt":"<string>"}}'

SDK

await services.ai.generateText({ prompt: "…" });

Inputs

FieldTypeRequiredDescription
enableWebSearchbooleanNoLet the model search the web before answering. Does not change the price.
promptstringYesWhat you want the model to do

Inputs may also be piped as NDJSON, one JSON object per line.

Output

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "text": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ]
    }
  },
  "required": [
    "text"
  ],
  "additionalProperties": false
}

The field that carries the answer is text. It is null — or empty — when nothing was found, which is how a miss is told from a hit without knowing anything else about this entry.

Before you run

  • Price it first. orangeslice ai text --dry-run returns the exact dollar cost and spends nothing.
  • Large runs need approval. Above the spend-gate threshold a run exits 7 until it carries a plan token, and only a dry run mints one.
  • Scopes: enrich
  • Permitted uses: research, outreach, export

Exit codes

0 ok · 2 bad input · 3 auth · 4 not found · 5 provider · 6 rate limited · 7 spend gate, nothing billed · 8 timeout · 9 a third-party account needs connecting