modeliddecisionnode-flash(todaydecisionnode-flash-0.9.1-rc1)- Answers
- Choice, Score, Truth, Number, Point and Box, each calibrated
- Serves
/v1/decide, sessions and batch jobs- Input
- The same fields as the full model: state, up to 16 images, questions
- Context
- 64k tokens per request
- Price
- $0.035 per 1M input tokens, output free
- Images and video
- $0.08 per 1M image and video tokens, no fee per image
- Batch jobs
- 50% off: $0.0175 per 1M input tokens
When to use it#
- High volume: moderation of every comment, triage of every event, scoring of every row.
- Inside a latency budget: a check on the hot path of a request, or a gate in front of every agent step.
- Clear decisions: short inputs and well separated options, where the full model's extra capacity is not needed.
Calling it#
curl https://api.decisionnode.com/v1/decide \
-H "Authorization: Bearer $DECISIONNODE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "decisionnode-flash",
"state": "Customer: I was charged twice and nobody has replied for 3 days.",
"questions": {
"route": {
"type": "choice",
"instructions": "Where should this go?",
"criteria": {
"billing": "money",
"bug": "broken",
"account": "login"
}
},
"urgency": {
"type": "score",
"instructions": "How urgent is this?",
"criteria": ["routine", "today", "urgent", "critical"]
},
"refund": {
"type": "truth",
"instructions": "Refund this automatically?"
}
}
}'Only model changes. At $0.035 per million, the 62-token request above costs $0.0000022, and a million of them about $2.17.
DecisionNode Flash is also what answers a DecisionNode request when DecisionNode has no ready capacity, unless the request opts out (how). DecisionNode Flash itself has no fallback: with no ready capacity it answers 529 with Retry-After.