$ cat /info
___ ___ ___ __ _ _ __ __ _
/ __|/ _ \/ __|/ _` | '_ \ / _` |
\__ \ (_) \__ \ (_| | | | | (_| |
|___/\___/|___/\__,_|_| |_|\__,_|
High-performance, low-cost API for image, video & text generation
$ cat /pricing
| # image models |
|
$0.0095 -76% |
per image |
|
$0.0095 -72% |
per image |
|
$0.0220 -67% |
per image |
|
$0.0275 -79% |
per image |
|
$0.0280 -72% |
per image |
|
$0.0350 -74% |
per image |
|
$0.0400 -74% |
per image |
|
$0.0500 -79% |
per image |
|
$0.0195 -61% |
per image |
| # video models |
|
$0.2000 -34% |
per second |
|
$0.5000 -27% |
per second |
| # text models |
|
$0.360 / $1.800 -88% |
per 1M tokens |
|
$0.900 / $4.500 -82% |
per 1M tokens |
|
$3.600 / $18.000 -64% |
per 1M tokens |
|
$0.065 / $0.390 -74% |
per 1M tokens |
|
$0.130 / $0.780 -91% |
per 1M tokens |
|
$0.520 / $3.120 -74% |
per 1M tokens |
|
$0.225 / $1.350 -78% |
per 1M tokens |
|
$0.562 / $3.375 -78% |
per 1M tokens |
|
$1.125 / $6.750 -78% |
per 1M tokens |
$ cat /status
$ cat /stability --model=▾
p05–p95
p50
last 7 days · hourly
$ cat /reliability
-
multi-provider routing
every request is balanced across multiple providers by live health — one provider going down never takes you down
-
automatic retries
failed generations are retried transparently, and you are never billed twice for the same result
-
prompt optimizer
prompts are auto-tuned before generation to minimize false moderation rejections
-
durable storage
every result is stored on redundant S3 and served over a fast CDN
-
low latency
median generation completes in seconds — see live numbers under /stability
-
lowest prices
images from $0.0095, text models up to 90% below official prices — the cheapest on the market
$ open /faq
$ cat /contact
$ cat /legal
$ ls /models
$