Pricing
What NeuroAPI's Starter, Pro, and Enterprise plans include, what each mode costs, and what happens at a limit.
Every successful /agent/ask debits one or more cost_units from your
quota, and everything else (/health, validation errors, rate-limited
rejections, server errors) is free. Each plan bundles a monthly quota
of cost units, a per-minute rate limit, an active-API-key
cap, a concurrent-run limit, and a support level.
Plans
| Plan | Price | Monthly quota | Rate limit (per key) | Runs at once | Modes | Active API keys | Support | SLA |
|---|---|---|---|---|---|---|---|---|
| Starter | $49 / month | 10,000 | 60 / min | 2 | fast, smart | up to 30 | Best-effort email | - |
| Pro | $299 / month | 100,000 | 60 / min | 5 | fast, smart, max | up to 100 | Standard email | - |
| Enterprise | Custom - talk to sales | from 1,000,000 | 300 / min | 10 | fast, smart, max | up to 100 | Dedicated | Contractual |
Quotas reset at the start of each monthly billing period. You need an active subscription to create keys.
What each mode does
The mode field on /agent/ask sets how deep the research goes:
| Mode | cost_units | Required plan | What it's for |
|---|---|---|---|
fast | 1 | All plans | Quick answers with core market knowledge. Good for asset checks, market sentiment, and high-volume financial Q&A. |
smart (default) | 2 | All plans | Deeper reasoning and more market context for complex questions. Good for technical analysis, trade setups, and fundamental stock research. |
max | 8 | Pro, Enterprise | The deepest research: multi-asset investigations and fundamental analysis with broad market coverage. Calling max on the Starter plan returns 403 mode_not_in_plan. |
When you don't pass mode, the server defaults to smart. See the
Billing guide for examples of how cost_units debit
your quota.
What counts against your quota
Whether a call is charged depends on its outcome:
| Outcome | Charged? |
|---|---|
200 from /agent/ask | Yes - debits cost_units |
200 from /health | No - free |
4xx (auth, validation, billing) | No - free |
5xx (server, capacity) | No - free |
How cost_units are debited
Read usage.cost_units on every successful response as the source of
truth for what you were charged. The last request of a period may be
charged fewer units than its mode's price.
Worked example
This table assumes every call is smart (the default, 2 units)
over a 30-day month:
| Daily traffic | Monthly cost units | Fits Starter (10,000)? | Fits Pro (100,000)? | Fits Enterprise (1,000,000)? |
|---|---|---|---|---|
| 100 calls / day | ~6,000 | Yes, 60% used | Yes, 6% used | Yes, <1% used |
| 1,000 calls / day | ~60,000 | No, exceeded | Yes, 60% used | Yes, 6% used |
| 10,000 calls / day | ~600,000 | No, exceeded | No, exceeded | Yes, 60% used |
Three more patterns:
- A side project running
~50smartcalls a day uses~3,000cost units a month, about 30% of Starter's quota. - A live product feature at
~500smartcalls a day uses~30,000a month, which needs Pro. - A
max-heavy research workflow at~100calls a day uses100 × 8 × 30 ≈ 24,000cost units a month. That is 24% of Pro's quota, andmaxneeds Pro or Enterprise.
When you hit a limit
| Status | Cause | What to do |
|---|---|---|
429 | Rate limit exceeded for the current minute, or the period's quota is spent. | Honor Retry-After, or wait for X-Quota-Reset. See the Rate limits guide. |
402 | A payment failed. | Open the dashboard → Billing & Plans. See the Errors guide. |
403 no_active_subscription | The account has no active subscription. | Subscribe in the dashboard → Billing & Plans. |
403 mode_not_in_plan | Selected mode isn't available on your plan (e.g. max on Starter). | Pick a lower mode, or upgrade to Pro. |