Generate images and video with the OpenAI SDK — no OpenAI key required

livepairai — Wed, 14 Oct 2026 01:41:37 +0000

The OpenAI Python SDK is mostly a base_url and an api_key. If an API speaks the same shapes — /images/generations, /chat/completions, /videos — the SDK you already have installed works against it.

LivePair exposes exactly that surface: an OpenAI-compatible endpoint covering 60+ image and video generation models (Seedream, Seedance, Wan, Qwen Image, Ideogram, Minimax) plus a set of chat models. One base_url change, and client.images.generate() produces media from models that don't exist on OpenAI.

Disclosure: I work on LivePair. Everything below is runnable against the live API — the catalog, prices, and shapes are public at GET /v1/agent/models.

Setup

pip install openai requests

Grab a key: sign up at livepairai.com → Settings → API keys → lp_…. Billing is a prepaid credit balance — each call debits the per-model price, no subscription.

from openai import OpenAI

client = OpenAI(
    base_url="https://livepairai.com/v1/agent",
    api_key="lp_...",          # sent as a Bearer token, so the stock SDK works
)

Images — `client.images.generate` just works

img = client.images.generate(
    model="seedream-5.0",
    prompt="a lighthouse on a cliff at dusk, cinematic lighting",
    size="1024x1024",
)
print(img.data[0].url)

That's the unmodified OpenAI call. The catalog decides what model can be — seedream-5.0, qwen-image-3, ideogram-3-turbo, and so on. size accepts the standard 1024x1024 / 1792x1024 / 1024x1792 values and maps onto each model's aspect-ratio ladder.

Chat — `client.chat.completions.create`

r = client.chat.completions.create(
    model="deepseek/deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Explain the CAP theorem in two sentences."}],
    max_tokens=256,
)
print(r.choices[0].message.content)

Video — Sora-shaped, poll-then-download

The video endpoint mirrors OpenAI's Videos API shape: POST /videos returns a job immediately, GET /videos/{id} polls status, GET /videos/{id}/content streams the mp4. Newer SDK releases have a client.videos namespace; here's the plain-HTTP version so the contract is visible:

import time, requests

H = {"Authorization": "Bearer lp_...", "Content-Type": "application/json"}
BASE = "https://livepairai.com/v1/agent"

job = requests.post(f"{BASE}/videos", headers=H, json={
    "model": "wan-3.0-t2v",
    "prompt": "drone shot over a foggy forest at dawn, slow push-in",
    "size": "1280x720",   # 16:9; 720x1280 → 9:16
    "seconds": "5",
}).json()

vid = job["id"]
while True:
    v = requests.get(f"{BASE}/videos/{vid}", headers=H).json()
    if v["status"] in ("completed", "failed"):
        break
    time.sleep(5)

if v["status"] == "completed":
    mp4 = requests.get(f"{BASE}/videos/{vid}/content", headers=H)  # 302 → media URL
    open("out.mp4", "wb").write(mp4.content)

Prices are data, not a pricing page

GET /v1/agent/models returns every model with a priceUsd field — the exact per-call debit before you make it:

models = requests.get(f"{BASE}/models").json()
for m in models["models"]:
    print(m["id"], m["mode"], m["priceUsd"])

GET /v1/agent/balance shows your prepaid balance and recent ledger entries.

Why bother

The useful part isn't another API key — it's that image gen, video gen, and chat land on the same OpenAI surface you already integrate, priced per call against a balance you can watch. For pipelines that need several model families (compare outputs, fallback chains, cost routing), switching models is a string, not a new provider account.

There's also a no-account path if you're wiring autonomous agents: the same endpoints answer 402 Payment Required and settle per call in USDC via x402, so a client that can sign a payment header can call without any signup at all.

Gotchas

n > 1 isn't supported on image generation — loop instead.
Video is async by design; budget ~1–3 min per clip depending on model.
A generation that fails provider-side refunds to the balance automatically.
Results aren't published anywhere and are deleted after 48h — save the bytes.

Docs: livepairai.com/docs, machine-readable spec at /v1/agent/openapi.json, MCP server for agent clients under /mcp.

I built an MCP server where AI agents pay for their own compute in USDC

livepairai — Fri, 09 Oct 2026 04:51:34 +0000

Agents can browse docs and call APIs, but they can't do checkout. No credit card form, no OAuth dance, no "verify your email". So when I shipped an AI generation API, the interesting question was: how does an agent pay?

What I built

An MCP server (https://livepairai.com/mcp, streamable HTTP) exposing ~70 image/video models behind one interface. An agent connects, lists models with prices, calls generate, and gets back either a result or an HTTP 402 with payment requirements.

The payment rail is x402 — USDC on Base. The flow:

POST /v1/agent/generate {model, prompt}
← 402 Payment Required

x-payment-requirements: {amount: "400000", currency: USDC, chain: base, payTo} → agent signs USDC transfer, retries with X-PAYMENT header ← 200 + result URL (hosted 48h, auto-deleted)

One HTTP round-trip pattern. No API key, no account, no session — the payment signature is the credential.

What actually happens inside

Model catalog with live per-call pricing: GET /v1/agent/models (5s 720p video ≈ $0.40, images ≈ $0.02–0.05)
Quote freshness was the annoying part — prices are per-result, so the 402 response carries a short-lived quote the agent must settle before expiry
For humans/API keys there's a chat-completions-compatible surface instead, so integrators who want accounting get Authorization: Bearer lp_… and skip the wallet dance entirely

Failure modes I hit

Agents that retry the original request without attaching payment — had to make the 402 body self-describing (amount, recipient, expiry, example header) so a generic agent could act on it without me hardcoding the client
Wallet-funded agents settling twice on timeout — made fulfillment idempotent on the payment reference
The privacy constraint shaped the storage layer: renders live 48h max, never indexed, share links are a separate opt-in path gated by model

Try it

MCP endpoint: https://livepairai.com/mcp
Agent docs: https://livepairai.com/SKILL.md
Manifest: https://livepairai.com/v1/agent/manifest.json

If your agent has a USDC wallet, it can already use this. Curious how others are handling

DEV Community: livepairai