Cheaper Inference
Cheaper Inference
d1 is available for structured decisions from Liquid AI. Its reported context window is 65,536 tokens. Reported inputs: image, text. The served catalog lists image input.
/v1/decisions
Ready when you are
Marketplace pricing, capped at list, optimized further.
d1/v1/decisionsPOST /v1/decisions
curl https://api.cheaperinference.com/v1/decisions \ -H "Authorization: Bearer ci_live_YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": "I was charged twice.", "model": "d1", "questions": [ { "name": "refund", "type": "predicate", "instructions": "Does the customer ask for a refund?" } ] }'Capability source · checked
| Model | Current pricing | Context limit | Image input listed |
|---|---|---|---|
| d1 (this model)Liquid AI | See model pricing | 65,536 tokens | Yes |
| d1-ultraLiquid AI | See model pricing | 32,768 tokens | Yes |
| jev-1.13.0TypeSafe | See model pricing | 32,000 tokens | Yes |
| jev-1.14.0TypeSafe | See model pricing | 32,000 tokens | Yes |
This model takes the fields in its sample request. It has no other stated parameters.
Compare recorded quotes and the hours with the highest observed discounts.
This model’s recorded quotes averaged 15.0% below recorded reference prices across the selected range. Its strongest observed window was 7:00 AM–5:00 AM in UTC.
Average quoted discount
15.0%
Highest discount time
7:00 AM–5:00 AM
Hourly coverage
23/24
Signal quality
Growing
Hover a bar for recorded unit discounts and observation counts.
Source buckets are UTC; labels are converted to UTC.
Last 24 hours
Not ranked
No qualifying activity in this window
Last 7 days
Unavailable
Activity could not be loaded
Last 30 days
Unavailable
Activity could not be loaded