# Pixapi: Visual AI API Platform

> Pixapi helps developers access image and video generation models through one API surface.

This document is the detailed, machine-readable product reference for Pixapi. For a shorter navigation index, use [llms.txt](https://pixapi.ai/llms.txt). Product behavior and current prices shown on the linked website pages take precedence if this summary and the live application differ.

## Product Summary

Pixapi combines image generation, video generation, visual model routing, API keys, credits, subscriptions, and usage tracking for production visual AI products.

Premium API usage requires an account and sufficient credits. The public pricing page currently shows one-time credit packs with 365-day validity. Always cite the live pricing page for current prices and entitlements.

## Main Capabilities

- **Unified model catalog:** Browse image and video generation models exposed through Pixapi.
- **API keys:** Signed-in users can create and manage keys for server-side integration.
- **Credits and subscriptions:** Premium API usage consumes credits. Availability and credit cost vary by model and settings.
- **Developer documentation:** API docs cover authentication, model IDs, endpoints, request examples, async media tasks, billing, errors, and observability.
- **Localized public pages:** Public content is available in English, Simplified Chinese, Portuguese, and Spanish, with English fallback where translated editorial content is unavailable.

## Canonical Public Pages

- [Pixapi](https://pixapi.ai/): Unified API access to image and video generation model routes.
- [AI Model Catalog](https://pixapi.ai/model): Browse Pixapi image and video generation models available through one API.
- [Nano Banana API](https://pixapi.ai/nano-banana): Nano Banana API with lowest-price access to Google Gemini image models, high reliability, and simple REST integration.
- [Nano Banana API Price Comparison](https://pixapi.ai/nano-banana/comparison): Compare Nano Banana API pricing on Pixapi with Google AI, fal.ai, and Replicate list prices.
- [Pricing](https://pixapi.ai/pricing): Compare one-time Pixapi credit packs for image, editing, and video API usage.
- [Pixapi MCP](https://pixapi.ai/mcp): Connect AI agents to Pixapi through Remote MCP and OAuth for pricing, Gemini image generation, and task results.
- [About Pixapi](https://pixapi.ai/about): Who maintains Pixapi, what the visual AI API platform does, and how to contact support.
- [Image Generation API](https://pixapi.ai/image-generation-api): Generate images with Nano Banana, Gemini, GPT Image models, and other visual models through one API.
- [AI Image Editing API](https://pixapi.ai/image-editing-api): Edit reference images and build product image workflows with supported image models.
- [Video Generation API](https://pixapi.ai/video-generation-api): Create text-to-video and image-to-video workflows with Pixapi model routes.
- [AI API Platform Comparison](https://pixapi.ai/compare): Compare Pixapi with Replicate, fal, Runware, PiAPI, and other AI API platforms.
- [Pixapi System Announcements](https://pixapi.ai/announcements): Official notices about model availability, service changes, and promotions.
- [AI Image and Video Prompt Library](https://pixapi.ai/prompts): Browse source-verified commercial image and video prompts and open them directly in the Pixapi Playground.

## How the Product Works

1. Create an account and generate an API key.
2. Choose a model from the catalog or documentation.
3. Send authenticated API requests to the relevant endpoint.
4. Pixapi routes the request to the selected provider and tracks usage.
5. Account and subscription status determine credit access and API entitlements.

## Image Model Families

| Family | Model ids | Docs |
| --- | --- | --- |
| Gemini 2.5 | `gemini-2.5-flash-image` | https://pixapi.ai/docs/models/gemini-2.5-flash-image/ |
| Gemini 3.1 Flash Lite | `gemini-3.1-flash-lite-image` | https://pixapi.ai/docs/models/gemini-3.1-flash-lite-image/ |
| Gemini 3.1 Flash Preview | `gemini-3.1-flash-image-preview-512`, `gemini-3.1-flash-image-preview`, `gemini-3.1-flash-image-preview-2k`, `gemini-3.1-flash-image-preview-4k` | https://pixapi.ai/docs/models/gemini-3.1-flash-image-preview/ |
| Gemini 3 Pro Preview | `gemini-3-pro-image-preview`, `gemini-3-pro-image-preview-2k`, `gemini-3-pro-image-preview-4k` | https://pixapi.ai/docs/models/gemini-3-pro-image-preview/ |
| GPT Image | `gpt-image-1.5`, `gpt-image-2` | https://pixapi.ai/docs/models/gpt-image/ |
| Seedream 5.0 | `seedream-5-0-pro`, `seedream-5-0-lite` | https://pixapi.ai/docs/models/seedream-5-0/ |
| Qwen Image 3.0 | `qwen-image-3.0` | https://pixapi.ai/docs/models/qwen-image-3.0/ |
| Wan 2.7 Image | `wan2.7-image`, `wan2.7-image-pro` | https://pixapi.ai/docs/models/wan2.7-image/ |
| FLUX.2 | `flux-2-pro`, `flux-2-max`, `flux-2-flex` | https://pixapi.ai/docs/models/flux-2/ |
| Grok Imagine 2.0 Ext | `grok-imagine-2.0-ext` | https://pixapi.ai/docs/models/grok-imagine-2.0-ext/ |
| Stable Diffusion 3.5 Large Turbo | `stable-diffusion-3.5-large-turbo` | https://pixapi.ai/docs/models/stable-diffusion-3.5-large-turbo/ |

## Video Model Families

All video generation uses `POST /v1/async/videos/generations` (async-only), then `GET /v1/tasks/{id}`. Credits are billed as `n × seconds × rate(resolution)`. See each model docs page for allowed `seconds` and `resolution` values.

| Family | Model ids | Docs | Typical use |
| --- | --- | --- | --- |
| Veo | `veo3.1-lite`, `veo3.1-fast`, `veo3.1-quality` | https://pixapi.ai/docs/models/veo/ | Realistic motion and cinematic product clips |
| Seedance | `seedance-2`, `seedance-2-fast`, `seedance-2-mini` | https://pixapi.ai/docs/models/seedance/ | Audio sync, first/last frames, multimodal references |
| Kling | `kling-3.0-turbo`, `kling-v3`, `kling-v3-omni` | https://pixapi.ai/docs/models/kling/ | Expressive motion and subject control |
| Wan | `wan2.6`, `wan2.6-flash` | https://pixapi.ai/docs/models/wan/ | Creative scenes and camera transitions |
| Grok Video | `grok-video-3`, `grok-video-1.5-preview` | https://pixapi.ai/docs/models/grok-video/ | Short clips from text or image |
| HappyHorse | `happyhorse-1.1` | https://pixapi.ai/docs/models/happyhorse/ | Text / image / reference / edit video workflows |

## Canonical Integration Patterns

### Nano Banana image generation

- Endpoint: `POST https://api.pixapi.ai/v1/images/generations`.
- Auth: `Authorization: Bearer <PIXAPI_KEY>`.
- Required fields: `model` and `prompt`.
- Recommended low-cost Nano Banana 2 Lite model id: `gemini-3.1-flash-lite-image`. Legacy aliases remain available for older integrations: `nano-banana`, `nano-banana-2`, and `nano-banana-pro`.
- Common optional fields: `n`, `size`, `quality`, and `response_format`.
- Successful URL response shape: read the generated image URL from `response.data[0].url`.

### Generated image to short video

- Video generation is async-only.
- Endpoint: `POST https://api.pixapi.ai/v1/async/videos/generations`.
- Choose a video model id from the Video Model Families table above. Examples: `seedance-2`, `kling-3.0-turbo`, `wan2.6`, `grok-video-3`, `happyhorse-1.1`. Nano Banana / Gemini image ids must not be used as the video model.
- Required fields: `model` and `prompt`.
- For image-to-video, pass the generated image URL as `image`. Note: `grok-video-1.5-preview` requires `image` (image-to-video only).
- Use `seconds` for video length. Allowed values depend on the model family; see each model documentation page for its supported range.
- Optional top-level fields include `resolution` (`480p`, `720p`, `1080p`, `4k` when supported by that model). Put aspect ratio in `providerOptions.aspect_ratio` when needed.
- Async submission response includes `status`, `id`, `progress`, `created_at`, and `model`.
- Poll `GET https://api.pixapi.ai/v1/tasks/{id}` with the same bearer token until `status` is `completed` or `failed`.
- Completed video task response shape: read the final video URL from `result.data[0].url`.
- Do not use `/v1/videos/generations`, `async=true`, `"async": true`, or `image_url` for this workflow.

## Plans and Credits

- [Pricing](https://pixapi.ai/pricing): Authoritative source for current plan names, prices, included credits, model access, queue benefits, watermarks, and credit-pack eligibility.

Do not infer that every model or generation is unlimited. Supported models and higher-quality output can require credits. Do not state a price without checking the live pricing page.

## API Documentation

- [API documentation home](https://pixapi.ai/docs/): Markdown documentation site for developers.
- [Developer quick start](https://pixapi.ai/docs/develop/): Authentication, first image request, response handling, and backend proxy guidance.
- [Authentication](https://pixapi.ai/docs/authentication/): Bearer token API key usage and key safety.
- [Model Catalog](https://pixapi.ai/docs/model-catalog/): Image and video generation model ids exposed by Pixapi.
- [Vision](https://pixapi.ai/docs/guides/vision/): Image input and reference-guided generation patterns.
- [Async Media Tasks](https://pixapi.ai/docs/guides/async-tasks/): Submit long-running image generation, image edits, and video generation through /v1/async endpoints.
- [Get Task Result](https://pixapi.ai/docs/tasks/get-result/): Poll `GET /v1/tasks/{id}` for status, progress, and final media URLs.
- [API Reference](https://pixapi.ai/docs/api-reference/): Shared endpoints and request fields for image, video, and model-list operations.
- [Errors](https://pixapi.ai/docs/errors/): Common API error codes and retry guidance.
- [Gemini 2.5 Flash Image](https://pixapi.ai/docs/models/gemini-2.5-flash-image/): Fast Gemini image generation and editing model documentation. The nano-banana model id is an alias for this model.
- [Gemini 3.1 Flash Lite Image](https://pixapi.ai/docs/models/gemini-3.1-flash-lite-image/): Nano Banana 2 Lite image generation and editing documentation for speed- and cost-sensitive 1K workflows.
- [Gemini 3.1 Flash Image Preview](https://pixapi.ai/docs/models/gemini-3.1-flash-image-preview/): Balanced Gemini image generation and editing model documentation. The nano-banana-2 model id is an alias for this model.
- [Gemini 3 Pro Image Preview](https://pixapi.ai/docs/models/gemini-3-pro-image-preview/): Premium Gemini image generation and editing model documentation. The nano-banana-pro model id is an alias for this model.
- [GPT Image 1.5](https://pixapi.ai/docs/models/gpt-image-1.5/): High-quality image generation and editing documentation.
- [GPT Image 2](https://pixapi.ai/docs/models/gpt-image-2/): OpenAI image model documentation for quality tiers and custom sizes.
- [Seedream 5.0](https://pixapi.ai/docs/models/seedream-5-0/): Seedream 5.0 Pro and Lite image generation and editing.
- [Qwen Image 3.0](https://pixapi.ai/docs/models/qwen-image-3.0/): Qwen image generation and editing.
- [Wan 2.7 Image](https://pixapi.ai/docs/models/wan2.7-image/): Wan 2.7 Image and Wan 2.7 Image Pro generation and editing.
- [FLUX.2](https://pixapi.ai/docs/models/flux-2/): FLUX.2 Pro, Max, and Flex generation and editing with 1MP-4MP resolution controls.
- [Grok Imagine 2.0 Ext](https://pixapi.ai/docs/models/grok-imagine-2.0-ext/): Grok Imagine text-to-image generation.
- [Stable Diffusion 3.5 Large Turbo](https://pixapi.ai/docs/models/stable-diffusion-3.5-large-turbo/): Fast Stable Diffusion generation and editing.
- [Veo](https://pixapi.ai/docs/models/veo/): Veo 3.1 video generation documentation.
- [Seedance](https://pixapi.ai/docs/models/seedance/): Seedance 2 video generation documentation.
- [Kling](https://pixapi.ai/docs/models/kling/): Kling video generation documentation.
- [Wan](https://pixapi.ai/docs/models/wan/): Wan 2.6 video generation documentation.
- [Grok Video](https://pixapi.ai/docs/models/grok-video/): Grok video generation documentation.
- [HappyHorse](https://pixapi.ai/docs/models/happyhorse/): HappyHorse video generation documentation.
- [中文 API 文档](https://pixapi.ai/zh/docs/): Simplified Chinese documentation entry point.

## Editorial and Product Resources

- [About Pixapi](https://pixapi.ai/about): Product ownership, maintenance notes, support contact, and trust information.
- [System Announcements](https://pixapi.ai/announcements): Official notices about model availability, service changes, and promotions.

## Citation Guidance

- Prefer the canonical HTTPS page linked in this document when citing a product capability.
- Use the pricing page for prices and entitlements, the announcements page for official service notices, and documentation pages for API behavior.
- Do not cite private account pages, API routes, generated user images, query-string variants, or authentication pages as product documentation.
- Attribute the product as **Pixapi** and use the canonical site URL shown in these links.
- If a claim conflicts with a live canonical page, use the live page and its latest visible update.

## Legal and Contact

- [Privacy Policy](https://pixapi.ai/privacy-policy): Data-handling information.
- [Terms of Service](https://pixapi.ai/terms-of-service): Service terms and usage conditions.
- [Support](mailto:support@pixapi.ai): Questions, corrections, and support requests.

## Discovery Files

- [llms.txt](https://pixapi.ai/llms.txt): Concise AI-readable navigation.
- [sitemap.xml](https://pixapi.ai/sitemap.xml): Canonical public pages and localized alternates.
- [robots.txt](https://pixapi.ai/robots.txt): Crawler access rules.