optimloptiml

start free. upgrade when the volume is real.

the free plan needs no card and has no time limit. upgrade when you need more requests, more seats, or the deployment controls.

free

$0

individuals and side projects.

2 projects, 5 workflows

1,000 requests/mo

1 seat, 1 server key

all providers, your own keys

traces, cost, and latency per request

community support

popular

startup

$49

/mo

small teams shipping to real users.

10 projects, 25 workflows

50,000 requests/mo

5 seats, 5 server keys

1 organization

a/b experiments

auto-graded evals

rollback + version history

team

$149

/mo

growing engineering teams.

unlimited projects & workflows

500,000 requests/mo

20 seats, 20 server keys

up to 5 organizations

everything in startup

enterprise

custom

high volume and a contract to match.

everything in team

unlimited requests and seats

unlimited organizations

dedicated support channel

custom contract

all plans include: direct inference through your existing openai-compatible client · your own provider keys · studio · conversations · per-step traces and latency, with cost recorded where the provider reports usage and estimated pricing labelled estimated. you pay providers directly for tokens; optiml never resells inference.

FAQ

what counts as a request?

one call to your deployed endpoint — whether it's a chat message, a classification, or anything else your workload handles.


do i need to provide my own LLM API keys?

yes. optiml runs your workloads through your provider keys, so the billing relationship with openai, anthropic and the rest stays yours. what you pay optiml is separate from what you pay them.


is there a free trial on paid plans?

no. the free plan is free to keep with no time limit, but paid plans take a card at checkout and start billing immediately. you can cancel at any time.


can i upgrade or downgrade anytime?

yes. plan changes take effect as soon as the payment provider confirms them — downgrades included, so a lower tier and its limits apply right away rather than at the end of the cycle.


what happens if i hit my monthly request limit on the free plan?

requests return a 429 until the next month resets (or you upgrade). your endpoints and data stay safe.


do you support sso, saml, or audit logs?

not yet. they are on the roadmap and are not part of any plan today. if they are a requirement for you, tell us — it moves them up the list.

connect one workload first

you get a baseline from your own traffic before you decide whether any of this is worth paying for.