# E2X

> E2X is an AI model API platform providing access to 16 AI models for image generation, video generation, upscaling, background removal, face swap, and more. One REST API, one API key, pay-per-use pricing with no minimums and no subscription required.

Jobs are submitted to a single asynchronous endpoint and polled (or delivered by webhook). Every model shares the same submit/poll contract, so switching models means changing one string. Costs are quoted in micro-cents (1,000,000 = $1 USD).

The site is published in 13 languages; see "Languages" below for the URL pattern.

Every public page is served in 13 languages. English (`en`) is the canonical, unprefixed version (`https://e2x.ai/models`); every other locale is the same path behind a two-letter prefix — `https://e2x.ai/tr/models`, `https://e2x.ai/de/models`, `https://e2x.ai/fr/models`. Requests to `/en/…` redirect to the unprefixed URL. Each page declares `hreflang` alternates for all locales plus `x-default`, and translations are content-equivalent: same models, same prices, same API.

Machine-readable documentation lives under `https://e2x.ai/files/llms/`. One model is documented at `/files/llms/models/<provider>/<model-id>/llms.txt` and one provider at `/files/llms/providers/<provider>/llms.txt`, where `<provider>` and `<model-id>` come from the model catalog linked below. These files are regenerated from the live catalog every 5 minutes.

Authentication: every API request carries a bearer API key issued from the dashboard at `https://e2x.ai/api-keys` (sign-in required; that area is not crawlable). Keys are account-scoped and carry the account balance — treat them as secrets and keep them server-side. There is no OAuth flow and no per-model key: one key works for the whole catalog. A missing or invalid key returns `401`; an insufficient balance returns a `402`-class error in `error.code`.

Submit a job:

```bash
curl -X POST https://api.e2x.ai/v1/jobs/submit \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "provider/model-id", "input": {"prompt": "your prompt"}}'
```

Then poll it (or pass `webhookUrl` in the submit body to get a callback instead):

```bash
curl https://api.e2x.ai/v1/jobs/{JOB_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

A job is `pending` (queued), `processing` (picked up by a worker), `completed` (outputs available in `data.outputs`), `failed` (reason in `data.error.message`) or `cancelled`.

Conventions: all costs are in micro-cents (1,000,000 = $1 USD). Quoted prices are the current effective prices — any active platform-wide discount is already applied, and the undiscounted figure is labelled as the list price. Model availability and pricing change over time. Fetch `/llms-full.txt` for the full input schema, parameters and worked request/response examples of every model.

## Site

- [Home](https://e2x.ai/): Platform overview and featured models
- [Models](https://e2x.ai/models): Browsable catalog of every model, with pricing and parameters
- [Providers](https://e2x.ai/providers): Model providers (Google, OpenAI, ...) and the models each one serves
- [Categories](https://e2x.ai/categories): Models grouped by task: text-to-image, image-to-image, text-to-video, image-to-video, ...
- [Pricing](https://e2x.ai/pricing): Pay-per-use pricing, credit packs, and plan comparison
- [Blog](https://e2x.ai/blog): Guides, model launches, and API walkthroughs

## API Documentation

- [Model catalog (llms.txt)](https://e2x.ai/files/llms/models/llms.txt): Every model with provider, category, price, status, and a link to its own llms.txt
- [Provider catalog (llms.txt)](https://e2x.ai/files/llms/providers/llms.txt): Every provider with model counts and per-provider documentation
- [Single model documentation (example: Nano Banana)](https://e2x.ai/files/llms/models/google/nano-banana/edit-image/llms.txt): Full input schema, parameters, pricing, and request examples for one model
- [Single provider documentation (example: google)](https://e2x.ai/files/llms/providers/google/llms.txt): All models served by one provider
- [Expanded documentation (llms-full.txt)](https://e2x.ai/llms-full.txt): This file plus the full documentation of every model inlined
- [API base URL](https://api.e2x.ai/v1): REST API root

## Languages

- [English (`en`)](https://e2x.ai/models): English — canonical, unprefixed URLs (`x-default`)
- [Turkish (`tr`)](https://e2x.ai/tr/models): Türkçe — every path behind the `/tr` prefix
- [German (`de`)](https://e2x.ai/de/models): Deutsch — every path behind the `/de` prefix
- [French (`fr`)](https://e2x.ai/fr/models): Français — every path behind the `/fr` prefix
- [Spanish (`es`)](https://e2x.ai/es/models): Español — every path behind the `/es` prefix
- [Italian (`it`)](https://e2x.ai/it/models): Italiano — every path behind the `/it` prefix
- [Portuguese (`pt`)](https://e2x.ai/pt/models): Português — every path behind the `/pt` prefix
- [Japanese (`ja`)](https://e2x.ai/ja/models): 日本語 — every path behind the `/ja` prefix
- [Korean (`ko`)](https://e2x.ai/ko/models): 한국어 — every path behind the `/ko` prefix
- [Chinese (`zh`)](https://e2x.ai/zh/models): 中文 — every path behind the `/zh` prefix
- [Russian (`ru`)](https://e2x.ai/ru/models): Русский — every path behind the `/ru` prefix
- [Hindi (`hi`)](https://e2x.ai/hi/models): हिन्दी — every path behind the `/hi` prefix
- [Indonesian (`id`)](https://e2x.ai/id/models): Bahasa Indonesia — every path behind the `/id` prefix

## Available Models

- [Nano Banana](https://e2x.ai/files/llms/models/google/nano-banana/edit-image/llms.txt): Edit existing images from a text prompt with Nano Banana — retouch, restyle or adjust details quickly and at low cost.
- [Nano Banana](https://e2x.ai/files/llms/models/google/nano-banana/text-to-image/llms.txt): Fast, cost-efficient text-to-image generation for everyday work. Quick turnarounds at a low per-image price.
- [Nano Banana 2](https://e2x.ai/files/llms/models/google/nano-banana-2/llms.txt): Fast, affordable image editing for everyday use.
- [Nano Banana 2](https://e2x.ai/files/llms/models/google/nano-banana-2/edit-image/llms.txt): Fast, affordable image editing for everyday use.
- [Nano Banana Pro](https://e2x.ai/files/llms/models/google/nano-banana-pro/edit-image/llms.txt): Better consistency and improved output quality.
- [Nano Banana Pro](https://e2x.ai/files/llms/models/google/nano-banana-pro/text-to-image/llms.txt): Google's gemini-3-pro-image model for text-to-image generation, with readable in-image typography and output up to 4096x4096.
- [GPT Image 2](https://e2x.ai/files/llms/models/openai/gpt-image-2/text-to-image/llms.txt): Generate images from text prompts using OpenAI gpt-image-2 , OpenAI Images Generations API.
- [Nano Banana 2 Lite](https://e2x.ai/files/llms/models/google/nano-banana-2-lite/text-to-image/llms.txt): Generate images from text prompts with Google Nano Banana 2 Lite. Lightweight, lower-cost variant with extended aspect ratios.
- [Nano Banana 2 Lite](https://e2x.ai/files/llms/models/google/nano-banana-2-lite/edit-image/llms.txt): Nano Banana 2 Lite reference-to-image generation. Generates images from text prompts and reference images. Lightweight, lower-cost variant with extended aspect ratios.
- [Veo 3.1 Fast](https://e2x.ai/files/llms/models/google/veo-3.1-fast/start-end-frame-to-video/llms.txt): Google Veo 3.1 Fast start-end frame to video generation. Faster processing with smooth video transitions between start and end frames.
- [Omni Flash](https://e2x.ai/files/llms/models/google/omni-flash/reference-to-video/llms.txt): Google DeepMind's latest video generation with high fidelity and diverse styles.
- [Omni Flash](https://e2x.ai/files/llms/models/google/omni-flash/text-to-video/llms.txt): Google DeepMind's latest video generation with high fidelity and diverse styles.
- [Veo 3.1 Fast](https://e2x.ai/files/llms/models/google/veo-3.1-fast/image-to-video/llms.txt): Google DeepMind video generation with high fidelity and diverse styles.
- [Veo 3.1 Fast](https://e2x.ai/files/llms/models/google/veo-3.1-fast/reference-to-video/llms.txt): Google DeepMind video generation with high fidelity and diverse styles.
- [Veo 3.1 Fast](https://e2x.ai/files/llms/models/google/veo-3.1-fast/text-to-video/llms.txt): Google DeepMind video generation with high fidelity and diverse styles.
- [GPT Image 2](https://e2x.ai/files/llms/models/openai/gpt-image-2/edit-image/llms.txt): GPT Image 2 reference-to-image generation. Generates images from text prompts and reference images.

## Categories

- [All categories](https://e2x.ai/categories): Every capability the catalog serves, with model counts
- [Image to Image](https://e2x.ai/categories/image-to-image): Transform images using AI-powered style transfer.
- [Image to Video](https://e2x.ai/categories/image-to-video): Animate still images into dynamic videos.
- [Reference to Video](https://e2x.ai/categories/reference-to-video): Transform reference images to dynamic videos
- [Start & End Frame To Video](https://e2x.ai/categories/start-end-frame-to-video): Create videos from start & end frame.
- [Text to Image](https://e2x.ai/categories/text-to-image): Generate images from text descriptions.
- [Text to Video](https://e2x.ai/categories/text-to-video): Create videos from text prompts.

## Optional

- [Terms of Service](https://e2x.ai/terms): Terms governing use of the platform
- [Privacy Policy](https://e2x.ai/privacy): How user and generation data is handled
- [Cookie Policy](https://e2x.ai/cookies): Cookie and consent details
- [Acceptable Use Policy](https://e2x.ai/acceptable-use): Content and usage restrictions
- [Sitemap](https://e2x.ai/sitemap.xml): Machine-readable index of every public URL in every locale
- [robots.txt](https://e2x.ai/robots.txt): Crawl policy, including named rules for AI crawlers