Comparisons

Arrakis vs Replicate

Replicate is an API for running open and partner models, most billed by the second or per output, with custom models packaged in Cog. Arrakis runs any Hugging Face model on a GPU of your own, with the engine and options you choose and root SSH, billed by the GPU-hour.

Side by side

As of 31 Oct 2026, 16:52 UTC, the lowest price for the NVIDIA B300 on Arrakis is $4.60 per GPU-hour, with 57 GPUs available on 8 machines.

ArrakisReplicate
B300 per GPU-hour$4.60/GPU-hrNot listed: its price list stops at the H200
B200 per GPU-hour$6.33/GPU-hrNot listed: its price list stops at the H200
H100 per GPU-hour$2.07/GPU-hr$5.49 ($0.001525 a second)
BillingBy the hour; a started hour counts in fullPer second; many models per output
How you payPrepaid balance: card, Link or Apple PayPrepaid credit
Root SSH and any Docker imageYesNo
Serverless endpoints, billed per requestNo: each model gets a GPU of its ownYes: models and deployments, per second
Hosted models, billed per outputNo: deploy any Hugging Face model yourselfYes: thousands of public models
MCP server for AI agentsYes, remote at /mcpYes: runs models, doesn't rent GPUs
Spend cap on each API keyYes, on every tokenNo caps per token
Automatic shutdownYes: every rental has a removal timeYes: scales to zero when idle
Interruptible machinesYes, where hosts offer themNo
Searches several GPU marketsYesNo: its own platform

Facts about other providers come from their own pages, checked on October 31, 2026. Prices and features change: check them before you choose. Arrakis is not affiliated with them.

Which fits you

Replicate fits better

You want to call thousands of ready models through one API, pay only while they run, and skip machines entirely.

Arrakis fits better

You want root SSH, any Docker image without packaging it in Cog, your own engine and options, or a flat hourly GPU price for steady traffic.

Moving to Arrakis

Your Docker image, SSH keys and scripts move as they are: Arrakis boots any public or private image with root SSH, and serves your own model with your own engine options. Start with one machine in the console, or point your agent at /mcp with a capped token.

Questions

When is Arrakis cheaper than Replicate?
When the GPU stays busy. On October 31, 2026, Replicate listed an H100 at $5.49 an hour, billed by the second, and many official models per output. A GPU on Arrakis costs its hourly price however many requests it serves.
Do I need Cog to run my model on Arrakis?
No. Arrakis runs any Hugging Face model on vLLM, SGLang, vLLM-Omni or llama.cpp, or any Docker image you bring, with root SSH.