Anthropic API: what it charges, what it allows, and what it keeps
thecontinuitylayer.com/inference-apis/anthropic-apiAnthropic's own API for its Claude models.
- 1Yes
Does Anthropic API publish a per-token price?
Yes, by Anthropic's own page.
The public docs list per-token prices for every model, e.g. Claude Sonnet 5.5 at $2 input / $10 output per 1M 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 Anthropic API publish its rate limits?
Yes, by Anthropic's own page.
The docs publish per-model limits on requests, input tokens and output tokens for each usage tier.
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 Anthropic API train on your API prompts by default?
No, by Anthropic's own page.
Anthropic says it does not train on API inputs or outputs unless the customer opts in or sends feedback.
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 Anthropic API say how long it keeps your prompts and outputs?
Yes, by Anthropic's own page.
Anthropic states retention for API data, with deletion within 30 days by default on its privacy pages and zero retention available by agreement; its API docs describe no retention by default except for some models that require 30 days.
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 Anthropic API run a public status page?
Yes, by Anthropic's own page.
Anthropic runs a public status page that lists the Claude API as its own component.
Yes means: A public page shows current uptime and past incidents.
Every grade above is read from Anthropic's own page on the day shown. If a page has changed, tell us.