Skip to content
DecisionNodeDecisionNdedocs
  • Guides
  • API reference
  • Examples
  • Playground

start here

  • QuickstartGet startedGet an API key, send one request with three questions, and branch your code on the typed answers. Plain HTTPS, no SDK to install.
  • POST /v1/decideAPI referenceAnswer typed questions about a state and optional images. One request, one buffered JSON response, one answer per question.
  • QuestionsConceptsQuestions say what to decide. Each one has a type that fixes the shape of its answer: a choice from your options, a score on your scale, a…
  • ConfidenceConceptsProbabilities are calibrated per question type, so a threshold means what it says.
  • ImagesConceptsSend images and text in the same request. The model reads printed and handwritten text, amounts, dates, objects and layout, and answers…
  • Batch jobsPatternsSend up to 10,000 requests in one file and collect the answers later, at half the live price.
  • Pricing and billingYou pay for input tokens only. Output is free because the model generates no text.
↑↓ moveopen7 suggestions
Get API keyGet API key
DecisionNodeDecisionNde

Get started

  • Introduction
  • Quickstart
  • Playground
  • Console and keys
  • With coding agents
  • Examples

Concepts

  • State
  • Questions
  • Choice
  • Score
  • Truth
  • Number
  • Images
  • Confidence
  • Determinism

Models

  • DecisionNode-1.0
  • DecisionNode-1.0 Flash
  • Limits
  • Versions
  • Dedicated capacity

Patterns

  • Confidence-gated routing
  • Fan-out
  • Guardrails
  • Control loops
  • Batch jobs

API reference

  • Overview
  • POST/v1/decide
  • GET/v1/models
  • Errors
  • Safety check
  • Rate limits

Sessions API

  • Sessions overview
  • POSTOpen a session
  • WSStream frames
  • DELEnd a session

Batch API

  • The batch object
  • POSTCreate a batch
  • POSTAdd requests
  • POSTFinalize a batch
  • GETRetrieve a batch
  • GETGet batch results
  • POSTCancel a batch
  • GETList batches

Pricing and billing

  • Pricing and billing

Policies

  • Responsible use
  • Data and privacy

Migrate

  • Coming from a Jev-shaped API
  • Benchmarks
  • Pricing
  • Playground
Get API key
  • Guides
  • API reference
  • Examples
  • Playground

Get started

  • Introduction
  • Quickstart
  • Playground
  • Console and keys
  • With coding agents
  • Examples

Concepts

  • State
  • Questions
  • Choice
  • Score
  • Truth
  • Number
  • Images
  • Confidence
  • Determinism

Models

  • DecisionNode-1.0
  • DecisionNode-1.0 Flash
  • Limits
  • Versions
  • Dedicated capacity

Patterns

  • Confidence-gated routing
  • Fan-out
  • Guardrails
  • Control loops
  • Batch jobs

API reference

  • Overview
  • POST/v1/decide
  • GET/v1/models
  • Errors
  • Safety check
  • Rate limits

Sessions API

  • Sessions overview
  • POSTOpen a session
  • WSStream frames
  • DELEnd a session

Batch API

  • The batch object
  • POSTCreate a batch
  • POSTAdd requests
  • POSTFinalize a batch
  • GETRetrieve a batch
  • GETGet batch results
  • POSTCancel a batch
  • GETList batches

Pricing and billing

  • Pricing and billing

Policies

  • Responsible use
  • Data and privacy

Migrate

  • Coming from a Jev-shaped API
  1. docs
  2. /
  3. Batch API

Finalize a batch

Lock a draft and queue it to run. Nothing runs before this call, and from it the expiry window counts.

on this page7 sections
  1. Authentication
  2. Path parameters
  3. Request body
  4. Response
  5. Errors
  6. Limits
  7. Notes
POSThttps://api.decisionnode.com/v1/batches/{id}/finalize
API=https://api.decisionnode.com/v1
BATCH=batch_01J9ZB8Q3T

curl -X POST "$API/batches/$BATCH/finalize" \
  -H "Authorization: Bearer $DECISIONNODE_API_KEY"

Authentication#

Authorizationheaderrequired
Bearer dn_live_..., the same key as every call. A batch belongs to the key that created it: other keys, even in the same workspace, get 404 for it.

Path parameters#

idstringrequired
The batch id that Create a batch returned, for example batch_01J9ZB8Q3T.

Request body#

None.

Response#

200 OK with the batch object in state queued, finalized_at set and expires_at 24 hours later.

200 OK
{
  "id": "batch_01J9ZB8Q3T",
  "state": "queued",
  "counters": {
    "requests": 3,
    "queued": 3,
    "in_progress": 0,
    "completed": 0,
    "failed": 0,
    "expired": 0,
    "cancelled": 0
  },
  "created_at": "2026-10-06T09:12:04Z",
  "finalized_at": "2026-10-06T09:12:31Z",
  "expires_at": "2026-10-07T09:12:31Z",
  "ended_at": null,
  "results_url": null,
  "results_expire_at": null,
  "price_factor": 0.5,
  "usage": { "input_tokens": 0, "output_tokens": 0 },
  "error": null
}
  1. Authentication
  2. Path parameters
  3. Request body
  4. Response
  5. Errors
  6. Limits
  7. Notes
request
API=https://api.decisionnode.com/v1BATCH=batch_01J9ZB8Q3Tcurl -X POST "$API/batches/$BATCH/finalize" \  -H "Authorization: Bearer $DECISIONNODE_API_KEY"

Errors#

  • 400

    Type
    api_usage_error
    When
    The batch holds no requests
    What to do
    Add requests first
  • 400

    Type
    api_usage_error
    When
    A line names a pinned model id that has retired; the message names it
    What to do
    Move those lines to the current id (or its alias) and create a new batch. The draft stays as it is; cancel it
  • 401

    Type
    authentication_error
    When
    The key is missing, unknown or revoked
    What to do
    Check the Authorization header
  • 404

    Type
    not_found_error
    When
    No batch with this id belongs to your key
    What to do
    Check the id and that you call with the key that created the batch
  • 409

    Type
    invalid_batch_state
    When
    The batch is no longer a draft: it was finalized or cancelled
    What to do
    Create a new batch for more requests
  • 429

    Type
    batch_limit_exceeded
    When
    Queuing it would put more than 100,000 requests in your key's active batches
    What to do
    Wait for a batch to end, then finalize again; the draft stays as it is
  • 429

    Type
    rate_limit_error
    When
    Over your request rate: batch calls count against it
    What to do
    Wait Retry-After seconds, then send the same call again
  • 500

    Type
    api_error
    When
    A fault on our side
    What to do
    Retry with backoff and jitter. A 5xx can come after the call took effect: before you create again, cancel any draft the failed create left behind (see Batch errors)
  • 529

    Type
    overloaded_error
    When
    The API cannot take the call right now
    What to do
    Wait Retry-After seconds, then retry with backoff
Errors this endpoint returns
StatusTypeWhenWhat to do
400api_usage_errorThe batch holds no requestsAdd requests first
400api_usage_errorA line names a pinned model id that has retired; the message names itMove those lines to the current id (or its alias) and create a new batch. The draft stays as it is; cancel it
401authentication_errorThe key is missing, unknown or revokedCheck the Authorization header
404not_found_errorNo batch with this id belongs to your keyCheck the id and that you call with the key that created the batch
409invalid_batch_stateThe batch is no longer a draft: it was finalized or cancelledCreate a new batch for more requests
429batch_limit_exceededQueuing it would put more than 100,000 requests in your key's active batchesWait for a batch to end, then finalize again; the draft stays as it is
429rate_limit_errorOver your request rate: batch calls count against itWait Retry-After seconds, then send the same call again
500api_errorA fault on our sideRetry with backoff and jitter. A 5xx can come after the call took effect: before you create again, cancel any draft the failed create left behind (see Batch errors)
529overloaded_errorThe API cannot take the call right nowWait Retry-After seconds, then retry with backoff

Every error body is {"detail": {"error_type": "...", "message": "..."}}. Retry 408, 429 (rate_limit_error), 529 and any 5xx, waiting at least what Retry-After says when it is set; fix the call for the other 4xx. A 429 batch_limit_exceeded clears only when a batch ends or you cancel one. All the bodies are on Errors.

Limits#

  • Requests in active batches per key

    Value
    100,000 across your drafts, queued and running batches
  • Unfinished requests

    Value
    Expire 24 hours after this call
Limits that apply to this call
LimitValue
Requests in active batches per key100,000 across your drafts, queued and running batches
Unfinished requestsExpire 24 hours after this call

Notes#

  • Results come with a multi-hour delay. There is no set time at which a batch runs or finishes, so poll for it.
  • Requests still unfinished 24 hours after a batch is finalized expire: they are not billed, and you can resubmit them.
  • Finalizing a batch that is no longer a draft answers 409 invalid_batch_state. If a finalize call timed out, retrieve the batch: queued means it went through.
  • A pinned model id that has retired is refused here, as on a live call: see Versions. An alias never retires, so lines that name an alias are never refused for it.
previousAdd requestsnextRetrieve a batch

DecisionNode is built and run by Bynn Intelligence, Inc.

  • Home
  • Playground
  • Examples
  • Console
  • Responsible use
  • Terms
  • Acceptable use
  • Privacy
  • Data processing
  • Defence addendum
  • Cookies