Question 1

What does it take to try it?

Accepted Answer

Two lines. Point the OpenAI or Anthropic client you already use at a Perdurance namespace URL and give it a Perdurance key instead of your provider key. The routes have your provider’s own names and take your provider’s own bodies, and the answer comes back byte for byte as the provider sent it — so no SDK is replaced, no response is unwrapped, and raising max_retries becomes safe rather than expensive.

Question 2

When is it not the right tool?

Accepted Answer

When your calls are short, your clients are stable, and re-running a failed request costs a cent — the failures it removes are ones you are not having, and this is still one more hop in your request path. It is also wrong if you want a hosted model, because it has none and you bring your own provider credential; if you need translation between provider dialects, which it deliberately does not do; if what you need made idempotent is your own tools rather than model calls; or if nobody outside your company may operate what your prompts pass through, because we operate every deployment, dedicated ones included.

Question 3

Do I have to change my code?

Accepted Answer

No. Change the base URL of the OpenAI or Anthropic client you already use, and use a Perdurance API key. Requests reach the provider byte for byte and answers come back exactly as the provider sent them, with no envelope — so an unmodified vendor SDK works against it, and the retry that SDK already performs becomes the resume mechanism.

Question 4

Why does a retried LLM request bill twice?

Accepted Answer

Because a retry is a second call to your provider. A client that loses its connection cannot tell whether the provider never received the request or is halfway through answering it, so it retries and pays for a second generation. Perdurance identifies a request by the bytes of its body for ten minutes, so an identical retry attaches to the execution already running and the provider is called once.

Question 5

What happens if my connection drops mid-stream?

Accepted Answer

Nothing is lost. The upstream call keeps running and every chunk continues to be stored whether or not anything is reading. Reconnect and the stream replays from the first chunk, or resumes at an exact sequence number, then live-tails to completion.

Question 6

Does it work with agent frameworks?

Accepted Answer

Yes. An agent stack usually retries at three layers — the vendor SDK, the framework step, and a supervisor or queue — and none of them knows the others already tried. Point the framework’s underlying provider client at Perdurance and every model call in the loop becomes idempotent, so a retry at any layer re-attaches instead of paying for a fresh generation.

Question 7

Do you see my prompts, and do you train on them?

Accepted Answer

Your prompts and responses are stored so you can read them back, and they are yours. No prompt, response or stored chunk is used to train, fine-tune or evaluate any model. Provider credentials are encrypted before storage and are never returned by any route. If that is still too much, an enterprise deployment keeps your traffic out of the shared service entirely.

Question 8

Can I have a deployment of my own?

Accepted Answer

Yes, as an enterprise deployment: one container image and one Postgres, dedicated to you, in our cloud or in your own cloud account. We operate it either way — you do not install it, patch it or carry the pager — and your prompts and provider keys stay in it rather than entering the shared service. It is priced as an annual agreement, per deployment or by volume.

Question 9

Which providers can it route to?

Accepted Answer

OpenAI and any server that copies its API, Anthropic’s Messages API, and OpenRouter including its Anthropic-family models. You bring your own provider credential and keep your own provider pricing; Perdurance does not resell model capacity.

Question 10

What does it cost?

Accepted Answer

$0.001 per request, billed on completion, with 50 MB of stored requests included and $10 per GB per month after that. There are no seats, no plan tiers and no minimum. Retries and reconnects inside the idempotency window bill once, and replaying a stored stream is free however many times you do it.

Legal notice

Who operates this service

What the service is

Intellectual property

Links and availability

The other documents

Applicable law