Results for “npu acceleration”

24 tools in Coding · Updated 2 Nov 2026

“npu acceleration”Coding › Sandboxes and infrastructureShowing 24 tools

Tinfoil Inferenceby TinfoilYC X25Call AI models through an attested confidential-inference APIPaid
SambaCloudby SambaNovaHosted inference API for large open-source models on SambaNova RDU hardwarePay as you go
ZenMLby ZenmlRun reproducible AI pipelines and agents on your chosen infrastructureFreemium
Sakana AIby Sakana AISakana AI API for Fugu orchestration models and the Japanese-focused Sakana Namazu LLM.Pay as you go
Novita AIby NovitaAIHosted model APIs, GPU infrastructure and agent sandboxes on one platformPay as you go
Liquid AIby Liquid AIEfficient foundation models for on-device and edge deployment.Freemium
SiliconFlowby SiliconFlowHosted inference API for open and commercial LLM and multimodal modelsPay as you go
DeepInfraby DeepInfraPay-per-token inference API for open-source and hosted AI modelsPay as you go
CoreWeave Serverless Inferenceby CoreWeavePay-per-token API access to open-source models and LoRA-tuned weights, with built-in tracing and evals.Pay as you go
Together Inferenceby Together AIPay-per-token API for running open-source models across text, image, video, code and voicePay as you go
Roboflow Inferenceby RoboflowYC S20Self-hosted computer vision inference server with WorkflowsFree
FastEmbedby QdrantLightweight Python library for generating text, sparse, image and reranking embeddingsFree
NVIDIA NIMby NVIDIAPrebuilt inference containers for running AI models on NVIDIA GPUsFreemium
Modalby ModalServerless cloud compute for AI inference, training, and sandboxed code.Freemium
Horizonby LabelboxRL training environments and evaluation data for AI reasoning and agent workContact sales
Inference Providersby Hugging FaceModel inference through multiple third-party providers, listed alongside pricing and performance metrics.Pay as you go
Hedraby HedraHosted inference and model-building service for visual and multimodal AIPay as you go
GroqCloudby GroqHosted API for running open-weight language and speech models on Groq hardwareFreemium
Chromaby ChromaOpen-source search infrastructure for AI apps, with the managed Cloud service being wound downFreemium
Claude Developer Platformby AnthropicUse Claude models and agent tools in your own applications through an API.Pay as you go
Replicateby ReplicateYC W20Cloud API for running, fine-tuning and deploying AI modelsPay as you go
Beamby BeamYC W22Persistent cloud VMs, sandboxes and GPUs for AI agentsPay as you go
Cerebriumby CerebriumYC W22Serverless GPU infrastructure for real-time AI workloadsFreemium
Relaceby RelaceYC W23API access to open-weight inference models, with additional tools and infrastructure for coding agents.Pay as you go