Munito AI
Munito is an open-model inference provider for Europe, private by default. Its API lets businesses choose their models and keep inference and storage in the EU.
Munito AI sells inference on Liquid Inference. A buyer names one of its models as munitoai/<model>, or names the model and pays the lowest offer that meets the buyer's rules.
Facts
- Handle
- munitoai
- Website
- https://munito.ai/
- On the exchange since
- 2026-10-19
- Models
- 10
- Offers
- 10
- Regions
- global
- Precisions (declared)
- fp8, nvfp4
- Lowest price on
- 3 of 10 models
Reliability, last 3 days
- Probes answered
- 98.99%
- Hours with an answer
- 100.0%
- Median response time
- 2.0s
Checked by the exchange
6 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
- DeepSeek V4 Flash 0731: declared precision fp8, global, $0.019 input and $0.048 output per million tokens, $0.0037 cache read per million tokens, 1M tokens of context
- DeepSeek V4 Flash 0731:thinking: declared precision fp8, global, $0.099 input and $0.250 output per million tokens, $0.019 cache read per million tokens, 1M tokens of context
- DeepSeek V4.1 Flash: declared precision fp8, global, $0.027 input and $0.101 output per million tokens, $0.00055 cache read per million tokens, 1M tokens of context
- DeepSeek V4.1 Flash 1017: declared precision fp8, global, $0.047 input and $0.174 output per million tokens, $0.00094 cache read per million tokens, 1M tokens of context
- DeepSeek V4.1 Flash 1017:thinking: declared precision fp8, global, $0.265 input and $0.983 output per million tokens, $0.0053 cache read per million tokens, 1M tokens of context
- DeepSeek V4.1 Flash:thinking: declared precision fp8, global, $0.270 input and $1.000 output per million tokens, $0.0054 cache read per million tokens, 1M tokens of context
- GLM 5.3 Flash: declared precision nvfp4, global, $0.045 input and $0.155 output per million tokens, $0.0093 cache read per million tokens, 1M tokens of context
- Kolibri 1: declared precision nvfp4, global, $0.130 input and $0.510 output per million tokens, $0.078 cache read per million tokens, 1M tokens of context
- Qwen 3.8 27B: declared precision nvfp4, global, $0.022 input and $0.297 output per million tokens, $0.0062 cache read per million tokens, 262.1K tokens of context
- Qwen 3.8 27b:thinking: declared precision nvfp4, global, $0.074 input and $0.987 output per million tokens, $0.021 cache read per million tokens, 262.1K tokens of context