DeepInfra: what it charges, what it allows, and what it keeps
thecontinuitylayer.com/inference-apis/deepinfraA hosted inference platform for open models, billed per token.
- 1Yes
Does DeepInfra publish a per-token price?
Yes, by DeepInfra's own page.
The public pricing page lists rates per model; Llama-3.3-70B-Instruct-Turbo costs $0.10 per 1M input tokens and $0.32 per 1M output tokens.
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 DeepInfra publish its rate limits?
Yes, by DeepInfra's own page.
The docs publish a default limit of 200 requests at once per model, and say how to ask for more.
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.
- 3Partly
Does DeepInfra train on your API prompts by default?
Partly, by DeepInfra's own page.
DeepInfra says it does not train on data sent to its APIs, except Google and Anthropic models, where those companies' training policies apply.
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 DeepInfra say how long it keeps your prompts and outputs?
Yes, by DeepInfra's own page.
Standard requests are held only in memory and deleted after the response, while image outputs and bulk jobs are kept for a short period it does not define.
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 DeepInfra run a public status page?
Yes, by DeepInfra's own page.
A public status page shows API and website uptime plus health checks for each model.
Yes means: A public page shows current uptime and past incidents.
Every grade above is read from DeepInfra's own page on the day shown. If a page has changed, tell us.