Quick start
OpenAI SDK
from openai import OpenAI
client = OpenAI(base_url="https://api.airoutly.com/v1")
resp = client.chat.completions.create(
model="gemini-2.5-flash",
messages=[{"role": "user", "content": "Hello"}],
)Pricing
| Per 1M tokens | Airoutly | Official |
|---|---|---|
| Input | $0.30 | |
| Output | $2.50 | |
| Cache read | — |
Ends 2026-11-10 23:59 UTC; the struck-through price applies afterwards.
About this model on Airoutly
Which model ID do I send?
Send
gemini-2.5-flash, the same ID Google uses.Is prompt caching supported?
Yes. Cached input is billed at the cache-read price above.