Skip to main content

Official Python SDK for RunBlob — all AI models in one place. Fast, affordable, high-quality generations. runblob.com

Project description

RunBlob Python SDK

Official async Python SDK for the RunBlob AI generation platform.

Currently supported: Nano Banana (Gemini) image generation, Kling video and image generation (12+ models including O1, O3, Motion Control), Veo 3 video generation (Fast, Quality, up to 4K), ChatGPT image generation and editing. More models coming in future updates.

For pricing, available models and API documentation visit runblob.com.

Install

pip install runblob

Configuration

from runblob import RunBlob

client = RunBlob(
    api_key="sk-...",
    max_connections=200,
    rate_limit_rps=100.0,
    max_retries=5,
    timeout=60.0,
    circuit_breaker_threshold=10,
)

Nano Banana (Gemini) — Image Generation

import asyncio
from runblob import RunBlob

async def main():
    async with RunBlob(api_key="sk-...") as client:
        result = await client.nanobanana.generate_and_wait(
            prompt="A cute orange cat on a windowsill",
            model="pro",
            quality="4k",
        )
        print(result.result_image_url)

asyncio.run(main())

Kling — Video Generation

async with RunBlob(api_key="sk-...") as client:
    result = await client.kling.generate_and_wait(
        prompt="A cinematic sunset over the ocean",
        model="kling_2.5_turbo",
        duration="10",
        aspect_ratio="16:9",
    )
    print(result.video_url)

Kling — O3 Video (up to 15s)

async with RunBlob(api_key="sk-...") as client:
    result = await client.kling.generate_o3_video_and_wait(
        prompt="A dog running through a field of flowers",
        model="kling_o3_pro",
        duration="15",
    )
    print(result.video_url)

Kling — O3 Photo (up to 4K)

async with RunBlob(api_key="sk-...") as client:
    result = await client.kling.generate_o3_photo_and_wait(
        prompt="A portrait in studio lighting",
        img_resolution="4k",
        aspect_ratio="3:4",
    )
    print(result.image_url)

Kling — Image-to-Video

async with RunBlob(api_key="sk-...") as client:
    result = await client.kling.generate_and_wait(
        prompt="Make this photo come alive",
        model="kling_2.1",
        image_url="https://example.com/photo.jpg",
    )
    print(result.video_url)

Veo 3 — Fast Video

async with RunBlob(api_key="sk-...") as client:
    result = await client.veo.generate_and_wait(
        prompt="A cinematic drone shot flying over a mountain lake at sunrise",
        model="veo_3_fast",
        aspect_ratio="16:9",
    )
    print(result.video_url)

Veo 3 — Quality 4K

async with RunBlob(api_key="sk-...") as client:
    result = await client.veo.generate_and_wait(
        prompt="Slow motion shot of rain drops falling on autumn leaves",
        model="veo_3_quality_4k",
        aspect_ratio="16:9",
    )
    print(result.video_url)

Veo 3 — Image-to-Video

async with RunBlob(api_key="sk-...") as client:
    result = await client.veo.generate_and_wait(
        prompt="Make this photo come alive with gentle camera movement",
        model="veo_3_fast",
        bytes_image="base64_encoded_image_here",
    )
    print(result.video_url)

ChatGPT — Image Generation

async with RunBlob(api_key="sk-...") as client:
    result = await client.chatgpt.generate_and_wait(
        prompt="A cute cat illustration in watercolor style",
        aspect_ratio="1:1",
    )
    print(result.result_image_url)

ChatGPT — Image Editing

async with RunBlob(api_key="sk-...") as client:
    result = await client.chatgpt.generate_and_wait(
        prompt="Remove the background and add a sunset",
        images=["https://example.com/photo.jpg"],
        aspect_ratio="4:3",
    )
    print(result.result_image_url)

Batch generation

async with RunBlob(api_key="sk-...") as client:
    results = await client.nanobanana.generate_batch_and_wait(
        prompts=[
            "A red apple on a white table",
            "A mountain peak covered in snow",
            "An anime girl with blue hair",
        ],
        model="standard",
        concurrency=5,
    )
    for r in results:
        print(r.result_image_url)

Webhooks

async with RunBlob(api_key="sk-...") as client:
    await client.kling.generate(
        prompt="A forest at dawn",
        callback_url="https://your-server.com/webhook",
    )
from runblob import parse_webhook_payload

event = parse_webhook_payload(request_body)
if event.is_completed:
    print(event.result_image_url)

Error handling

from runblob import RunBlob, AuthenticationError, RateLimitError, RunBlobError

async with RunBlob(api_key="sk-...") as client:
    try:
        result = await client.kling.generate(prompt="test")
    except AuthenticationError:
        print("Invalid API key")
    except RateLimitError as e:
        print(f"Rate limited, retry after {e.retry_after}s")
    except RunBlobError as e:
        print(f"SDK error: {e}")

Requirements

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

runblob-0.3.0.tar.gz (31.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

runblob-0.3.0-py3-none-any.whl (31.4 kB view details)

Uploaded Python 3

File details

Details for the file runblob-0.3.0.tar.gz.

File metadata

  • Download URL: runblob-0.3.0.tar.gz
  • Upload date:
  • Size: 31.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.11

File hashes

Hashes for runblob-0.3.0.tar.gz
Algorithm Hash digest
SHA256 b9972e3bc0a71ed13dc2edfbf3249a5a512b97419bee195fb5128da16b98a06f
MD5 07d68d5fbad1f59370104a2275fa076b
BLAKE2b-256 84c99d746513d65ee1c15735b0e4fc41e14c0450bd9e135cb81601f7268e670f

See more details on using hashes here.

File details

Details for the file runblob-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: runblob-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 31.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.11

File hashes

Hashes for runblob-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 01468c661415c2a7c9458e80bfca1a6ccc2a03ee88e47d25bcf12866ab74bb74
MD5 e55ff2955a5af8088c1467cecfdfd7d5
BLAKE2b-256 7812d8f20c56c3aa3c41dd2645be1c217f083cbcd1db390cac0292f2f8f7124d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page