RunPod through Squiid

On-demand GPU pods and serverless endpoints at community prices. RunPod is on the Squiid roadmap.

Roadmap Provisioned Provisioned. Squiid creates the project or account for you and keeps the provider keys.

What RunPod is

RunPod is a GPU cloud. You can rent a pod with a specific card and keep it running with a persistent volume, or deploy a serverless endpoint that scales workers up and down per request with a queue in front. Templates cover common inference and training images, network volumes hold model weights between runs, and the community cloud tier offers machines from independent hosts at lower prices than the secure cloud. Endpoints expose a simple run and status API, so calling your own model looks the same in code as calling a hosted provider.

For AI-coded projects RunPod is the option when the job needs a specific GPU for a sustained period: fine-tuning a model on your own data, serving a custom model that no hosted provider offers, batch rendering, or training runs that would cost far more on a hyperscaler. Serverless endpoints are the more common shape in production, because idle pods bill whether or not anyone is using them. Availability varies by card and region, which is worth knowing before a pipeline depends on one specific GPU type being free.

Why connect it through Squiid

RunPod is on the Squiid roadmap. When it is connected, Squiid will provision the account, hold the API key and route calls to https://api.squiid.io/v1/runpod/... with Authorization: Bearer $SQUIID_API_KEY, with SDKs working by base URL swap (gateway convention). GPU seconds and storage will be metered against prepaid credits at RunPod's list price with no markup, which matters especially for pods: a persistent pod left running is the single most common way to lose a few hundred dollars in an AI side project, and a prepaid balance with visible daily spend is a better guardrail than a card on file.

  • One account, one key, one bill, one dashboard. RunPod sits beside every other service your project uses, on the same invoice and the same credit balance.
  • Key custody. Squiid holds the RunPod credentials. Your code carries SQUIID_API_KEY, so RUNPOD_API_KEY, RUNPOD_ENDPOINT_ID never land in a repository, a preview deployment or an agent’s context.
  • Metering you can see. Every call is counted per service and per day, so you know what RunPod costs before the month ends.
  • Pause on zero. When prepaid credits run out the gateway stops authorizing usage instead of running up a bill you did not fund.
  • One rotation. Rotating the Squiid key cuts off every agent, worker and deployment at once, with no provider key to hunt down.

What you get

  • On-demand GPU pods and serverless endpoints
  • Network volumes for model weights
  • Community and secure cloud tiers
  • Per-second metering with daily spend visibility
  • RunPod list pricing, no markup

How to connect RunPod

One variable replaces the provider credentials this service would normally need. Requests go to the gateway and the official SDKs work by pointing their base URL at it (gateway convention).

# .env
# replaces RUNPOD_API_KEY, RUNPOD_ENDPOINT_ID
SQUIID_API_KEY=sq_live_xxxxxxxxxxxxxxxxxxxxxxxx

# every request: https://api.squiid.io/v1/runpod/...
# header:       Authorization: Bearer $SQUIID_API_KEY
01

Add it in your dashboard

Open the Squiid catalog, add RunPod and fund credits. Squiid provisions the project and keeps the provider keys.

02

Put the one key in your env

Add SQUIID_API_KEY to .env and delete RUNPOD_API_KEY, RUNPOD_ENDPOINT_ID. Nothing else from RunPod needs to exist in your project.

03

Point your agent at it

Claude Code, Cursor and Codex read the same variable and call https://api.squiid.io/v1/runpod/. Agents deploy a serverless endpoint and call it like any other HTTP model API, keeping pods for interactive training work only.

Pricing through Squiid

RunPod charges per second of GPU time by card type plus storage on volumes, at the provider's listed price. Squiid passes that through at par: one dollar of prepaid credit is one dollar of RunPod usage, with no markup and no per-request margin.

RunPod has no subscription attached on Squiid today. If a plan is required for a feature you need, it passes through at the provider’s listed price with no Squiid fee.

Squiid adds no markup to provider prices. There is a free plan at $0 a month with a 15% fee when you top up credits, Solo at $19.97 a month with a top-up fee that starts at 8% and falls to 3.5% as your spend grows, Team from $29.97 a seat a month with the same ladder one point lower, and Custom with a rate of 3% or less. Credits are prepaid, so RunPod usage stops when the balance reaches zero rather than producing an invoice you did not fund. Auto top-up with a cap keeps production running without handing anyone an open-ended card.

If you leave

Export: images, templates and functions are rebuilt from your source in your own RunPod account, and nothing persistent is left behind. Squiid never owns your code, your schema or your domain, and the gateway speaks RunPod's own API, so the client change is a base URL. The handover page lists what happens for every provider in the catalogue.

Works with every coding agent

RunPod through Squiid is just an HTTP call with a bearer token, so every agentic coding tool can use it with the single key already in your environment:

Vibe coding a feature on RunPod usually means asking for it in plain language and letting the agent write the integration. Because the key is Squiid’s rather than the provider’s, it can do that without ever holding a credential that could be leaked, logged or committed.

Related services

Questions people ask

Is RunPod available on Squiid now?

Not yet. It is on the roadmap and will be provisioned by Squiid when it opens.

Will idle pods still cost money?

Yes, a running pod bills whether or not it is busy. That is why serverless endpoints are usually the better default, and why prepaid credits act as a ceiling.

RunPod or Modal?

Modal defines infrastructure in Python and scales from zero automatically. RunPod rents specific GPUs more cheaply, including a community tier. Both will sit behind one Squiid key.

Can I bring my own container?

Yes. RunPod runs custom images for both pods and serverless workers, which Squiid does not restrict.

How will billing appear?

As GPU seconds and storage at RunPod's list price on your single monthly Squiid invoice, drawn from prepaid credits.

Connect RunPod with one key.

RunPod rents GPUs by the second as persistent pods or autoscaling serverless workers, with a community tier priced below the hyperscalers. Planned for Squiid with per-second metering.