Ray 2 Flash: Benchmarks, Pricing & Context Window

import requests

# Create the generation. wait="auto" long-polls (up to 60s) so most short
# jobs return as "completed" in a single round-trip.
res = requests.post(
    "https://gateway.llm-stats.com/v1/generations",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "ray-flash-2",
        "input": {"prompt": "A timelapse of clouds moving across the sky"},
        "wait": "auto",
    },
)
job = res.json()

# If it didn't finish inside the wait window, poll the same resource.
while job["status"] in ("queued", "running"):
    res = requests.get(
        f"https://gateway.llm-stats.com/v1/generations/{job['id']}",
        params={"wait": 60},
        headers={"Authorization": "Bearer YOUR_API_KEY"},
    )
    job = res.json()

if job["status"] == "completed":
    print("video:", job["output"]["media"][0]["url"])
else:
    print("Failed:", job["error"]["message"])