Groq

Live·4 models

Open-weight models served fast enough that latency stops being the thing you design around.

Lowest latencyCheap open weightsHigh throughput

4 models on Groq

Groq's own rate for each of these. Where another provider serves the same model it may charge differently — the model page shows every route side by side.

Model	Price	Context
Llama 3.1 8B Instructmeta/llama-3.1-8b-instruct	$0.050 in$0.080 out	131K
GPT-OSS 20Bopenai/gpt-oss-20b	$0.075 in$0.300 out	128K
GPT-OSS 120Bopenai/gpt-oss-120b	$0.150 in$0.600 out	131K
Llama 3.3 70B Instructmeta/llama-3.3-70b-instruct	$0.590 in$0.790 out	131K

Availability and latency

Multigrid does not measure Groq's availability, and will not publish numbers it did not measure.

For live status, read Groq’s own status page — it is the only authoritative source, and the one they update during an incident. Our own reachability probes against every provider are on the status page, and they answer “is anyone home”, not “is it fast”.

What Multigrid can tell you is what happened to your own requests: latency, errors and cost per provider are on your analytics page, measured from traffic you actually sent.

How this provider is reached

Wire format: openai
Base URL: https://api.groq.com/openai/v1
Route order: Ranked by price, per model: where another provider serves the same model more cheaply, that one is tried first. Your own key outranks every platform route.
Billing: We hold a platform key, so usage can be charged to your Multigrid balance. Your own key, if you add one, is still preferred over ours.

Data handling and compliance

Multigrid does not publish Groq’s retention window, training terms or certifications. We hold no audit report for them, have no contract obliging them to anything beyond their ordinary API terms, and could not tell you if any of it changed tomorrow — so anything stated here would be hearsay in a document your own auditor may read.

Their own documentation is authoritative and stays current without us. What we can tell you is what Multigrid does with the request on our side, which is on the Trust Center.

Groq docs Their status page

Use in a policy

Prefer, or exclude, Groq on any request. The slug is what the gateway matches on.

"provider": {
  "order": ["groq"],
  "allow_fallbacks": true
}

Provider preferences docs

Reach Groq on one balance

We hold a platform key for Groq, so everything above is reachable on Multigrid credit — one balance across every vendor, at the prices listed. Signing up takes no card and commits you to nothing. If you already have a Groq contract, bring that key instead and we take no percentage on the traffic.

Create an account Bring your own key