DreamcatcherAI
The center of gravity for sparse inference. Sparse-aware LLM token serving by Dreamcatcher AI.
DreamcatcherAI sells inference on Liquid Inference. A buyer names one of its models as dreamcatcherai/<model>, or names the model and pays the lowest offer that meets the buyer's rules.
Facts
- Handle
- dreamcatcherai
- Website
- https://dreamcatcher.co/
- Terms of service
- https://www.dreamcatcher.co/terms
- Privacy policy
- https://www.dreamcatcher.co/privacy
- On the exchange since
- 2026-10-16
- Models
- 1
- Offers
- 1
- Regions
- us-central
- Precisions (declared)
- BFP8
- Lowest price on
- 1 of 1 model
Reliability, last 3 days
- Probes answered
- 98.97%
- Hours with an answer
- 92.9%
- Median response time
- 2.7s
Checked by the exchange
0 of 1 offer matches the fingerprint of the model. 0 have a finished evaluation.
The exchange sends fixed prompts to each offer and compares the answers with a baseline for the model. It also runs benchmarks against the offers and keeps the results.
Data handling
- Kept 30 days, in review
- No training, in review
Models
- Kimi K3.1 Pro: declared precision BFP8, us-central, $1.790 input and $8.899 output per million tokens, $0.180 cache read per million tokens, 1M tokens of context