Groq through Squiid

Very fast inference for open models on custom LPU hardware. Groq is next up on Squiid, being built now.

Next up Instant Instant access. A usage-metered API that works the moment you add it to your dashboard.

What Groq is

Groq is an inference provider rather than a model lab. It hosts open-weight models on custom Language Processing Unit hardware and serves them through an OpenAI-compatible API, with tokens per second that are typically several times what a GPU-hosted copy of the same model returns. It also serves speech models for fast transcription. Because the API keeps the OpenAI shape, moving a route from a frontier provider to Groq is a configuration change rather than a rewrite, which is how most teams end up trying it.

Speed changes what you can build. In a vibe-coded app Groq is the provider you pick for anything a human is waiting on: autocomplete that has to keep up with typing, a voice agent where a pause reads as a failure, streaming UI that should finish before the user looks away, or an agent loop that makes twenty small model calls per action and cannot afford a second each. It is usually paired with a frontier model, fast tier in front and a careful tier behind.

Why connect it through Squiid

Running two or three providers means two or three keys, which is the problem Squiid exists to remove. Groq is provisioned instantly, the upstream key stays with Squiid, and calls go to https://api.squiid.io/v1/groq/... with Authorization: Bearer $SQUIID_API_KEY. OpenAI-compatible clients work by pointing their base URL at the gateway (gateway convention). Tokens are metered at Groq's published per-model rate against your credits, shown beside every other service in the dashboard, and settled on one invoice. Auto top-up with a ceiling keeps a latency-critical route funded without handing anyone an open-ended card.

  • One account, one key, one bill, one dashboard. Groq sits beside every other service your project uses, on the same invoice and the same credit balance.
  • Key custody. Squiid holds the Groq credentials. Your code carries SQUIID_API_KEY, so GROQ_API_KEY, GROQ_BASE_URL 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 Groq 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

  • Open-weight models on LPU hardware at high tokens per second
  • OpenAI-compatible endpoints through the gateway
  • Fast speech to text on the same key
  • Latency-tier and quality-tier providers under one credential
  • Groq list pricing, no markup

How to connect Groq

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 GROQ_API_KEY, GROQ_BASE_URL
SQUIID_API_KEY=sq_live_xxxxxxxxxxxxxxxxxxxxxxxx

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

Add it in your dashboard

Open the Squiid catalog, add Groq and fund credits. Access is instant and metered per request.

02

Put the one key in your env

Add SQUIID_API_KEY to .env and delete GROQ_API_KEY, GROQ_BASE_URL. Nothing else from Groq 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/groq/. Agents commonly wire Groq into streaming routes and voice pipelines where time to first token decides whether the feature feels broken.

Pricing through Squiid

Groq charges per input and output token by model, and per audio hour for speech models, at the provider's listed price. Squiid passes that through at par: one dollar of prepaid credit is one dollar of Groq usage, with no markup and no per-request margin.

Groq 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 Groq 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

Nothing to move: Groq is usage-metered, so leaving means creating your own Groq key and pointing the client at it. Squiid never owns your code, your schema or your domain, and the gateway speaks Groq'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

Groq 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 Groq 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

Why use Groq instead of calling the model at another provider?

Groq hosts open-weight models on its own hardware for much faster token output. The model may be the same, the latency is not.

Can Cursor set up a Groq streaming route with my Squiid key?

Yes. Cursor writes the route against the OpenAI-compatible client and reads SQUIID_API_KEY from the environment, with no Groq key in the project.

Does Groq work for voice agents through Squiid?

Yes. Groq's speech models are reachable on the same gateway path and metered per audio hour at Groq's list price.

Is Groq the same company as Grok?

No. Groq is an inference hardware and cloud company. Grok is xAI's model family, listed separately in this catalog.

How is Groq usage shown on my bill?

As a line on your single monthly Squiid invoice, with per-model token counts visible in the dashboard as they accrue.

Connect Groq with one key.

Groq runs open-weight models on its own LPU inference hardware, returning tokens far faster than general purpose GPUs. Through Squiid it is billed per token at Groq's list price.