Liquid Inference — lowest price for every prompt
Providers compete on price for every AI request. You pay the lowest offer that meets your rules.
The Inference
Public sector is Salesforce's fastest-growing business at scale, and OpenAI and NVIDIA now ship into US g
Nari Labs — Multimodal Inference at the Speed of Light
Ship multimodal models with lower latency and higher efficiency. Explore optimized model APIs, dedicated enter
sference: Managed Inference for Open Models
The managed inference platform for open-weight models, fine-tunes, and distilled models. Low-latency realtime
Quixotic AI: AI inference for the JVM at native speed
Run LLMs, vision, embeddings, and text-to-speech on the JVM at native speed. No Python runtime, ONNX bridges,
vLLM — Fast, Memory-Efficient LLM Inference & Serving
vLLM is a high-throughput and memory-efficient inference and serving engine for Large Language Models (LLMs).
AI-Native Cloud | DigitalOcean
Run AI products in production with a unified stack for agents, inference, and cloud—built for control, perform
Energy-Efficient AI Chips for Edge Devices & Embedded Systems | Efficient Computer
Efficient Computer builds the world's most energy-efficient general-purpose AI chips, delivering up to 10
Fermion Research · Local language models and runtimes
Fermion Research develops Neutrino local language models, ternary QAT methods, model formats, and inference ru
Intelligence shaped by you - Feyn
Train custom models on your data. Keep learning in production. Run faster and cheaper inference. Own the weigh
Mulga | Run AWS workloads on any compute, zero re-write
Spinifex runs AWS APIs on compute you own. Shift AI inference to better GPUs, storage to somewhere cheaper, an
Nola - ask the LLM in TypeScript
Nola is a TypeScript superset (.tsi) where LLM inference is a language feature: ask for typed values or let th
On-Demand AI Compute | Beam
Run sandboxes, task queues, and custom model inference with ultrafast boot times, instant autoscaling, and a d
Liquid Foundation Models - Liquid Docs
Liquid Foundation Models (LFMs) are a new class of multimodal architectures built for fast inference and on-de