import asyncio

async def fetch(client, prompt, sem):
    async with sem:                      # never more than N in flight
        return await client.complete(prompt)

async def main(client, prompts, limit=10):
    sem = asyncio.Semaphore(limit)
    tasks = [fetch(client, p, sem) for p in prompts]
    # return_exceptions keeps one failure from cancelling the rest
    results = await asyncio.gather(*tasks, return_exceptions=True)

    ok  = [r for r in results if not isinstance(r, Exception)]
    bad = [r for r in results if isinstance(r, Exception)]
    print(f"{len(ok)} ok, {len(bad)} failed")
    return ok

asyncio.run(main(client, prompts))