blackfuel
blackfuel sells inference on Liquid Inference. A buyer names one of its models as blackfuel/<model>, or names the model and pays the lowest offer that meets the buyer's rules.
Facts
- Handle
- blackfuel
- Website
- https://blackfuel.ai/
- On the exchange since
- 2026-10-11
- Models
- 5
- Offers
- 8
- Regions
- eu, global
- Precisions (declared)
- bf16, fp8, nvfp4
- Lowest price on
- 2 of 5 models
Reliability, last 3 days
- Probes answered
- 99.80%
- Hours with an answer
- 100.0%
- Median response time
- 3.0s
Checked by the exchange
3 of 8 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, declared by the provider
- No training, declared by the provider
- SOC 2 Type II, declared by the provider
- ISO 27001, declared by the provider
Models
- DeepSeek V4 Flash 0731: declared precision fp8, global, $0.015 input and $0.177 output per million tokens, $0.0030 cache read per million tokens, 1M tokens of context, the cheapest of 2 offers
- DeepSeek V4.1 Flash 1017: declared precision fp8, global, $0.049 input and $0.196 output per million tokens, $0.0098 cache read per million tokens, 1M tokens of context
- DeepSeek: Ai/deepseek V4.1 Flash 1017:eu: declared precision fp8, eu, $0.490 input and $1.470 output per million tokens, $0.098 cache read per million tokens, 1M tokens of context
- Gemma 4 31B Splituntied: declared precision bf16, global, $0.100 input and $0.299 output per million tokens, $0.020 cache read per million tokens, 262.1K tokens of context, the cheapest of 2 offers
- GLM 5.3: declared precision nvfp4, global, $0.120 input and $0.041 output per million tokens, $0.024 cache read per million tokens, 1M tokens of context, the cheapest of 2 offers