zro
zro sells inference on Liquid Inference. A buyer names one of its models as zro/<model>, or names the model and pays the lowest offer that meets the buyer's rules.
Facts
- Handle
- zro
- Website
- https://moonmath.ai/
- On the exchange since
- 2026-09-29
- Models
- 4
- Offers
- 5
- Regions
- eu, us
- Precisions (declared)
- fp8, provider-managed
- Lowest price on
- 2 of 4 models
Reliability, last 3 days
- Probes answered
- 98.80%
- Hours with an answer
- 100.0%
- Median response time
- 1.3s
Checked by the exchange
2 of 5 offers match the fingerprint of the model. 1 has 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
- No training, declared by the provider
Models
- DeepSeek V4.1 Flash: declared precision fp8, us, $0.300 input and $1.200 output per million tokens, $0.0060 cache read per million tokens, 1M tokens of context
- Dolly 1 Security: declared precision fp8, eu, $0.450 input and $1.500 output per million tokens, $0.090 cache read per million tokens, 1M tokens of context
- Gemini 4 Argon: declared precision fp8, us, $1.800 input and $9.000 output per million tokens, $0.090 cache read per million tokens, 1M tokens of context, the cheapest of 2 offers
- GLM 5.3 Flash: declared precision fp8, eu, $0.150 input and $0.500 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context