# Greenference Open-weight LLMs with Zero Data Retention, full GDPR compliance and European Union located servers. Greenference sells inference on Liquid Inference. A buyer names one of its models as greenference/\, or names the model and pays the lowest offer that meets the buyer's rules. ## Facts - Handle: greenference - Website: https://greenference.com/ - Terms of service: https://greenference.com/legal/terms - Privacy policy: https://greenference.com/legal/privacy - Status page: https://greenference.com/status - On the exchange since: 2026-10-08 - Models: 10 - Offers: 10 - Regions: eu-central - Precisions (declared): fp8 - Lowest price on: 7 of 10 models ## Reliability, last 3 days - Probes answered: 0.00% - Hours with an answer: 0.0% ## Checked by the exchange 0 of 10 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 ## Models - [Gemma 4 31B It](https://liquidinference.ai/models/gemma-4-31b-it.md): declared precision fp8, eu-central, $0.171 input and $0.483 output per million tokens, $0.066 cache read per million tokens, 131.1K tokens of context - [GLM 4.7 Flash](https://liquidinference.ai/models/glm-4.7-flash.md): declared precision fp8, eu-central, $0.081 input and $0.469 output per million tokens, $0.016 cache read per million tokens, 202.8K tokens of context - [GLM 5.3 Flash](https://liquidinference.ai/models/glm-5.3-flash.md): declared precision fp8, eu-central, $0.115 input and $0.460 output per million tokens, $0.023 cache read per million tokens, 1M tokens of context - [GPT: OSS 20B](https://liquidinference.ai/models/gpt-oss-20b.md): declared precision fp8, eu-central, $0.010 input and $0.052 output per million tokens, $0.0052 cache read per million tokens, 32.8K tokens of context - [Qwen 3 14B](https://liquidinference.ai/models/qwen3-14b.md): declared precision fp8, eu-central, $0.087 input and $0.262 output per million tokens, $0.044 cache read per million tokens, 16.4K tokens of context - [Qwen 3 30B a3b](https://liquidinference.ai/models/qwen3-30b-a3b.md): declared precision fp8, eu-central, $0.109 input and $0.328 output per million tokens, $0.055 cache read per million tokens, 8,192 tokens of context - [Qwen 3 32B](https://liquidinference.ai/models/qwen3-32b.md): declared precision fp8, eu-central, $0.109 input and $0.328 output per million tokens, $0.055 cache read per million tokens, 16.4K tokens of context - [Qwen 3 8B](https://liquidinference.ai/models/qwen3-8b.md): declared precision fp8, eu-central, $0.092 input and $0.287 output per million tokens, $0.046 cache read per million tokens, 32.8K tokens of context - [Qwen 3.5 9B](https://liquidinference.ai/models/qwen3.5-9b.md): declared precision fp8, eu-central, $0.046 input and $0.075 output per million tokens, $0.023 cache read per million tokens, 16.4K tokens of context - [Qwen 3.6 27B](https://liquidinference.ai/models/qwen3.6-27b.md): declared precision fp8, eu-central, $0.172 input and $1.552 output per million tokens, $0.086 cache read per million tokens, 16.4K tokens of context ## Related pages - [This page in a browser](https://liquidinference.ai/providers/dfb068db-7c5c-4676-9f62-5cd86a642db3) - [All providers](https://liquidinference.ai/providers.md) - [All models](https://liquidinference.ai/models) - [Discover the best model for your budget](https://liquidinference.ai/discover) - [Quickstart](https://liquidinference.ai/docs/quickstart.md) - [llms.txt: the index of every page, as Markdown](https://liquidinference.ai/llms.txt) - [llms-full.txt: every page in one file](https://liquidinference.ai/llms-full.txt)