API reference · Context.dev

context-dev/identify-transaction

Integrate this model through SandBase's unified API, with production-ready schemas and examples.

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run
Model IDcontext-dev/identify-transaction
01

Input Schema

9 parameters · 1 required · 8 optional

ParameterTypeRequiredDescription
transaction_infostringRequiredThe raw transaction descriptor to identify, e.g. 'SQ *COFFEE BAR 4157...' or 'AMZN Mktp US*2K4TZ'. · Min length: 3 · Max length: 500
mccunionOptionalMerchant Category Code from the transaction, used to narrow the business category.
citystringOptionalCity to prioritize when searching for the merchant.
phoneunionOptionalPhone number from the transaction, used to verify the match.
maxSpeedbooleanOptionalOptimize for speed: Context.dev skips time-consuming enrichment for a faster response at the cost of less comprehensive data. Default false.
timeoutMSintegerOptionalUpstream timeout in milliseconds (max 300000). Context.dev aborts the call with a 408 when exceeded. Keep it below the endpoint's requestTimeoutMs so the provider answers before the platform's own budget expires. · Min: 1000 · Max: 300000
country_glstringOptionalTwo-letter ISO 3166-1 alpha-2 country code (e.g. 'us', 'gb', 'de'). Must be one of Context.dev's supported countries. · Min length: 2 · Max length: 2
force_languagestringOptionalForce the language of the returned brand copy (a language NAME, e.g. 'english', 'french', 'japanese'). · Min length: 2
high_confidence_onlybooleanOptionalRun an extra verification pass and only return a match Context.dev is confident about. Default false.
02

Output Schema

FieldTypeDescription
idstringUnique identifier for the generation task
statusstringTask status: pending, running, completed, failed, timeout
modelstringModel used for the generation
outputsarrayArray of output items
outputs[].urlstringURL of the generated artifact
outputs[].content_typestringMIME type (e.g. image/png, video/mp4)
errorobject | nullError details if failed, null on success
error.typestringMachine-readable error type code
error.messagestringHuman-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

  1. Submit — POST to /v1/run, receive an id
  2. Poll — GET /v1/run/{id} until status is completed, failed, or timeout
  3. Retrieve — Read outputs from the completed response
03

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "context-dev/identify-transaction",
  "prompt": "a beautiful sunset over mountains"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"