AI infrastructure tools - pricing and status

Enterprise Ray platform for scaling AI workloads. Endpoints API for LLMs.

Pay per token

Cerebras Cloud provides ultra-fast AI inference powered by Cerebras Wafer-Scale Engine hardware, delivering some of the fastest token generation speeds available.

from $0.100/1M

Fast inference API for image and video models. Flux, SDXL and more.

Pay per token

Fastest inference for open source models. Specialises in Llama and Mistral.

from $1.40/1M

Ultra-fast AI inference API. Runs open-source models like Llama and Mixtral at very high speed.

from $0.0500/1M

from $0.0650/1M

from $0.150/1M

Serverless cloud for running AI models and Python functions.

Pay per token

Unified API for 200+ AI models. Route to the cheapest or fastest provider automatically.

Pay per token

from $0.0500/1M

Run open source AI models via API. Pay per second of compute time.

from $5.00/1M

Fast inference API for open source models. Competitive pricing vs OpenAI.

from $0.0500/1M