Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.flex.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Free credit

Every new account is granted $10 of free credit on signup. No card required — you can evaluate all text, image, video, and audio models before paying anything. When the free credit runs out, your next API call returns 402 Payment Required. Add a card from the dashboard to continue; any credit you add is spent down at the same per-model rates.

​
How we bill

Dollar-denominated, per-request. We don’t sell token bundles, we don’t subscribe you — we meter what you use:
Model typeUnit
Text / chat / completions / reasoningPer million input tokens, per million output tokens.
Image generationPer image.
Video generationPer second of output video.
Text-to-speechPer character of input text.
Speech-to-textPer minute of input audio.
Per-model pricing is in the catalog. Spend appears in the dashboard within a few minutes of each request.
Streaming a chat completion and stopping early still bills for the tokens that were generated before you closed the connection — the model did the work. Set max_tokens to cap worst-case spend.

​
Rate limits

Per-API-key, per-minute. Limits are set by tier:
These numbers are generated from backend/api_rate_limiter.py and backend/lago_client.py in the token-service repo. They update automatically when those files change.
TierRequests per minute
Free (default on signup)10
Elevated (approved users)60
Paid300
Every new signup is granted $10 of free credit. The tier is stored on the key. If you need more than the free tier, request an upgrade from the dashboard or email support@flex.ai. Every response from the API carries rate-limit headers:
HeaderMeaning
x-ratelimit-limit-requestsRPM ceiling for this key.
x-ratelimit-remaining-requestsRequests left in the current window.
x-ratelimit-reset-requestsUnix timestamp when the window resets.
When you exceed the limit you get 429 Too Many Requests with a Retry-After header (seconds to wait). Don’t retry in a tight loop — back off until the header’s deadline.

​
When credit runs out

Our API returns 402 Payment Required with this body: 
{
  "error": {
    "message": "Insufficient credit. Add funds at https://tokens.flex.ai/dashboard/billing to continue.",
    "type": "insufficient_quota",
    "code": "402"
  }
}
Once you add credit, subsequent requests succeed immediately — no key regeneration needed.

​
Adding a card

From dashboard/billing:
  1. Click Add payment method.
  2. Enter card details (processed by Stripe; we never see the number).
  3. Top up by any amount ≥ $5. The balance is added to your account immediately.
There’s no auto-recharge at launch — you’ll get an email when your balance drops below 5andagainwhenithits5 and again when it hits 0.