Image generation API
Generate images through LumeAPI with GPT Image, Gemini Image, Seedream, and more — published per-image rates on one gateway and wallet.
Text and image models share one API key. See per-model docs for resolution and async behavior.
Official reference vs LumeAPI catalog rates. Pricing unit: per image generation. Last updated: July 2026. Source: provider list price.
| Model | Official (in / out) | LumeAPI (in / out) | Savings | |
|---|---|---|---|---|
| Gemini 3.1 Flash Image · 1K/2Kgemini-3.1-flash-image-preview | $0.0735 | $0.05 | — | Details → |
| Gemini 3.1 Flash Image · 1K/2Kgemini-3.1-flash-image-preview-2k | $0.50 | $0.08 | — | Details → |
| GPT Image 2 · 1Kgpt-image-2-1k | $0.0584 | $0.05 | — | Details → |
| GPT Image 2 · 2Kgpt-image-2-2k | $0.17 | $0.08 | — | Details → |
| Seedream 5doubao-seedream-5.0 | $0.15 | $0.035 | — | Details → |
| Qwen Image 2.0qwen-image-2.0 | $0.03 | $0.03 | — | Details → |
| Nano Banana Progoogle/gemini-3-pro-image-preview | $0.134 | $0.134 / image | — | Details → |
Image generation API products often start text-only and add visuals later. LumeAPI lets you keep one API key and wallet when you add GPT Image, Gemini Image, or Seedream catalog models.
Per-image rates vary by resolution and model id—compare 1K vs 2K entries before promising unlimited images in your SaaS plan.
Read per-model docs for synchronous vs async behavior and required parameters.
Quote customer-facing “images per month” only after you pick resolution-specific model ids—1K and 2K entries have different catalog rates.
Store generation parameters in your product database so support can reproduce user issues with the same model id and size settings.
LumeAPI is designed for developers who want to integrate without scheduling demos. Create an account, confirm your email, and open Console to generate an API key. Fund your USD wallet with USDT on supported chains when you are ready for billable traffic—there is no mandatory minimum beyond what your tests require.
Point your OpenAI-compatible client at https://api.lumeapi.site/v1, set Authorization to Bearer your key, and pass a catalog model id in the model field. Run a short curl or SDK script from /docs to verify latency, streaming, and error handling before you attach the key to production services.
Use Usage logs to reconcile per-call cost with finance forecasts. When a model tier is too expensive or quality is insufficient, change model id—not your entire integration. For cross-provider price tables and Research deep dives, follow internal links on this page rather than duplicating migration math here.
Every catalog model has a detail page under /models with official reference pricing, LumeAPI pricing, and links to /docs/models/{id} for parameters and curl examples. Start there when this commercial page points you to a model id you have not called before.
The /docs index lists gateway authentication, Chat Completions, image endpoints, and async video patterns. llms.txt bundles the same information for agent tooling—useful when you want a single URL to paste into Cursor or an internal bot.
Research articles explain why bills grow and how to compare providers; commercial pages like this one explain what LumeAPI offers and how to start. Follow internal links instead of searching for duplicate migration content across pages.
If billing, chain deposits, or integration behavior is unclear, use /contact for support channels. Include your model id, approximate request time, and whether the issue is authentication, balance, or model parameters—that speeds up resolution.
GPT, Claude, and Gemini catalog ids with published per-token or per-media rates — not obscure small models marketed as discounts.
Official reference vs LumeAPI columns on every commercial page. Your request model id matches Usage logs and billing.
One base URL for Chat Completions, image generations, and async video. Swap key, base URL, and model id — keep your SDK.
Top up with USDT, create keys in Console, and track per-call cost in Usage — no sales calls required.
Three values change: API key, base URL, model id. Everything else stays the same.
# Separate image provider SDK
from openai import OpenAI client = OpenAI(api_key="YOUR_LUMEAPI_KEY", base_url="https://api.lumeapi.site/v1") # See /docs/models/gpt-image-2-1k for exact image endpoint and parameters
Full step-by-step rollout, streaming checks, and FAQ: Image API documentation →
API key, base URL (https://api.lumeapi.site/v1), and model id to a LumeAPI catalog entry. Message shape stays OpenAI-compatible for most apps.
Streaming, tool calling, JSON mode, and error handling on your heaviest models. Shadow 5–10% of traffic before full cutover.
Provider-native features (Anthropic Batch, Google Grounding, OpenAI Assistants) may require the official API. Test your exact payload.
Keep environment variables for base URL and model id. Switch back instantly if staging tests fail.
Image models bill per generation at published catalog rates.
Yes. One wallet for text and image.
gpt-image-2-1k, gemini-3.1-flash-image-preview, doubao-seedream-5.0, etc.
Image endpoints documented in /docs per model.
Add generation to your product with per-image catalog pricing.
Marketing and social assets with GPT Image or Gemini Image.
Compare 1K vs 2K model ids and per-image cost.
Follow per-model docs for synchronous vs async generation.
Yes on catalog image models — see /docs/models/{id}.
See table and model detail pages.
Gemini image models in catalog — same gateway.
Different model ids for 1K, 2K, etc.
See /video-generation-api.
See /ai-api-pricing.
Call image models through https://api.lumeapi.site/v1. Need help choosing a model? Browse the developer docs or contact support.
LumeAPI