Anyscale
Anyscale
✓ 22 Aug 2026
Managed Ray for distributed training and inference, either hosted or inside your own cloud account.
Infra
Inference APIs, routers and GPUs you rent by the second.
12 products
editorially ranked — placement is never sold
Baseten
Baseten
✓ 22 Aug 2026
Model deployment with fast cold starts and per-minute billing, so idle time costs nothing.
DeepInfra
DeepInfra
✓ 22 Aug 2026
Token-metered serving for open-weight models at some of the lowest published rates, with no contracts or upfront cost.
Fireworks AI
Fireworks
✓ 17 Aug 2026
Low-latency open-model serving with tuned deployments and function calling.
Groq
Groq
✓ 17 Aug 2026
Custom silicon delivering very high tokens-per-second on open models.
Lambda
Lambda
✓ 22 Aug 2026
On-demand GPU instances billed by the minute with no egress fees, from a company that also builds the hardware.
Modal
Modal
✓ 17 Aug 2026
Serverless GPUs for your own inference and training jobs, billed per second with a free starter allowance.
Ollama
Ollama
✓ 17 Aug 2026
Run open models locally on your own machine.
OpenRouter
OpenRouter
✓ 17 Aug 2026
One API key, hundreds of models, automatic failover.
Replicate
Replicate
✓ 17 Aug 2026
Run thousands of community models by the second — image, video, audio, text.
RunPod
RunPod
✓ 22 Aug 2026
Per-second GPU rental across Community and Secure Cloud tiers, plus serverless inference workers.
Together AI
Together
✓ 17 Aug 2026
Fast serverless inference and fine-tuning for open-weight models, billed per token.