Groq: what it charges, what it allows, and what it keeps
thecontinuitylayer.com/inference-apis/groqAn inference API that serves open models on Groq's own hardware, billed per token.
- 1Yes
Does Groq publish a per-token price?
Yes, by Groq's own page.
The public models page lists rates per 1M tokens; GPT OSS 120B costs $0.15 input and $0.60 output, though some enterprise models say contact sales.
Yes means: Per-token prices are on a public page with no sign-in. Partly means only some models are priced in public, or the price sits on a model page rather than the pricing page.
- 2Yes
Does Groq publish its rate limits?
Yes, by Groq's own page.
The docs publish request and token limits for each model, for example 30 RPM and 8K TPM for gpt-oss-120b, with a note that exceptions may apply.
Yes means: The docs give request or token numbers for each tier or model. Partly means some numbers, such as a concurrency cap or the top tiers only; no means the numbers are only shown inside a signed-in account.
- 3No
Does Groq train on your API prompts by default?
No, by Groq's own page.
The services agreement bars Groq from using customer inputs or outputs to train any model unless the customer gives explicit permission.
Yes means: Here no is the good answer: the provider's page says what you send its API is not used for training unless you opt in. Yes means it is unless you opt out; partly means it depends on the plan, the tier or the upstream provider.
- 4Yes
Does Groq say how long it keeps your prompts and outputs?
Yes, by Groq's own page.
Inference data is not retained by default, but inputs and outputs may be logged for up to 30 days for troubleshooting or abuse checks; every customer can switch on zero retention.
Yes means: A stated period, or a statement that nothing is kept by default. Partly means a period for some users or requests but not others.
- 5Yes
Does Groq run a public status page?
Yes, by Groq's own page.
A public status page shows uptime for each production and preview model.
Yes means: A public page shows current uptime and past incidents.
Every grade above is read from Groq's own page on the day shown. If a page has changed, tell us.