Boundless
Boundless sells inference on Liquid Inference. A buyer names one of its models as boundless/<model>, or names the model and pays the lowest offer that meets the buyer's rules.
Facts
- Handle
- boundless
- Website
- https://boundless.network/
- On the exchange since
- 2026-10-06
- Models
- 4
- Offers
- 4
- Regions
- us
- Precisions (declared)
- fp8
- Lowest price on
- 0 of 4 models
Reliability, last 3 days
- Probes answered
- 99.01%
- Hours with an answer
- 100.0%
- Median response time
- 4.3s
Checked by the exchange
3 of 4 offers match 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
- Zero retention, in review
- No training, in review
Models
- DeepSeek V4 Flash 0731: declared precision fp8, us, $0.060 input and $0.180 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context
- DeepSeek V4.1 Flash: declared precision fp8, us, $0.060 input and $0.200 output per million tokens, $0.0030 cache read per million tokens, 1M tokens of context
- DeepSeek V4.1 Flash 1017: declared precision fp8, us, $0.080 input and $0.350 output per million tokens, $0.0016 cache read per million tokens, 1M tokens of context
- GLM 5.3 Flash: declared precision fp8, us, $0.070 input and $0.202 output per million tokens, $0.014 cache read per million tokens, 1M tokens of context