PixelDojo API
AI Image and Video API Platform
Build with 150+ AI image, video and audio models through one REST API. Submit an async job, poll or use a webhook, and get output URLs back. It uses the same credits as the web app, with plans from $10/month.
API Reference
Public docs
Endpoints, schemas, and examples.
OpenAPI 3.1
Typed integrations
SDK generation and machine-readable specs.
LLM Docs
Agent-ready docs
llm.txt and agent integration help.
API Keys
Authentication
Create keys for apps and agents.
Usage Dashboard
Requests and credits
Monitor volume, logs, and balance.
Buy Credits
Prepaid capacity
Top up for image and video usage.
On sale now
Veo 3.1 20% off · through October 8 · applied automatically to every API call and tool run
Seedance 2 Reference
Original price 20 credits. Sale price 16 credits. 20 percent off.
Veo 3.1 Fast
Original price 4.5 credits. Sale price 3.6 credits. 20 percent off.
Veo 3.1 Standard
Original price 12 credits. Sale price 9.6 credits. 20 percent off.
Veo 3.1 Lite
Original price 2 credits. Sale price 1.6 credits. 20 percent off.
Available Models
150 AI models for image, video and audio generation behind one async control plane
Bria 3.2
Bria 3.2: text-to-image with 9 aspect ratio presets at 1K resolution, optional image and prompt enhancement, and photography/art medium hints.
/api/v1/models/bria-3-2/run
Ernie
Baidu Ernie text-to-image. Multilingual prompts and built-in prompt expansion.
/api/v1/models/ernie/run
FLUX
FLUX family on Replicate. Schnell, Dev, Pro, Kontext, Ultra, and LoRA remix variants in one entrypoint.
/api/v1/models/flux/run
Flux 2 Flex
Max-quality with up to 10 reference images
/api/v1/models/flux-2-flex/run
Flux 2 Klein 4B
Very fast generation and editing with up to 5 reference images
/api/v1/models/flux-2-klein-4b/run
Flux 2 Klein 9B
4-step distilled FLUX.2 [klein] foundation model for flexible control
/api/v1/models/flux-2-klein-9b/run
Flux 2 Pro
High-quality with up to 8 reference images
/api/v1/models/flux-2-pro/run
Flux 2 Max
The highest fidelity image model from Black Forest Labs
/api/v1/models/flux-2-max/run
Flux 2 Dev
Fast quality with up to 4 reference images
/api/v1/models/flux-2-dev/run
Flux 2 Klein 9B + LoRA
Klein 9B with custom LoRA support and up to 5 reference images
/api/v1/models/flux-2-lora/runFlux 2 Dev + LoRA
Flux 2 Dev with your own FLUX.2 [dev] LoRAs and up to 4 reference images
/api/v1/models/flux-2-dev-lora/run
FLUX 3 Image
Black Forest Labs FLUX 3: photoreal text-to-image up to 4K, edits with up to 10 reference images, and web-grounded generation for real products and places.
/api/v1/models/flux-3-image/run
Flux Dev
High-quality development model with configurable steps and guidance. For LoRAs, use Flux Dev Multi LoRA.
/api/v1/models/flux-dev/run
Flux Krea Dev
Photorealistic generation that avoids the oversaturated AI look. Supports a single LoRA via lora_weights.
/api/v1/models/flux-krea-dev/run
Flux Dev Multi LoRA
Flux Dev with multiple stacked custom LoRAs for complex style combinations.
/api/v1/models/flux-dev-multi-lora/run
Flux 1.1 Pro
Latest pro model with enhanced quality and strong prompt adherence.
/api/v1/models/flux-1.1-pro/run
Flux 1.1 Pro Ultra
Highest quality Flux model with raw mode for natural-looking images.
/api/v1/models/flux-1.1-pro-ultra/run
Flux Kontext Pro
Advanced model with state-of-the-art performance for both generation and editing.
/api/v1/models/flux-kontext-pro/run
Flux Kontext Max
Premium model with maximum performance and improved typography for generation and editing.
/api/v1/models/flux-kontext-max/run
Google Gemini Flash
Fast generation with Gemini 2.5 Flash
/api/v1/models/gemini-flash/run
Google Nano Banana Pro
SOTA with accurate typography and reasoning
/api/v1/models/nano-banana-pro/run
Google Nano Banana 2
Next-generation SOTA model with stronger consistency
/api/v1/models/nano-banana-2/runGoogle Nano Banana 2.1
Sharper layouts and subject consistency, with more precise edits
/api/v1/models/nano-banana-2-1/run
Google Nano Banana 2 Lite
Faster, lower-cost Nano Banana 2 at fixed 1K resolution
/api/v1/models/nano-banana-2-lite/run
GPT Image 2
OpenAI GPT Image 2: next-generation image model with 4K rendering and sharper text fidelity.
/api/v1/models/gpt-image-2/runGPT Image 2.5
OpenAI GPT Image 2.5 in two variants: Sunburst for premium reference-faithful renders and edits, Flare for the same quality tier at half the latency. Up to 4K output, optional reference images and masks.
/api/v1/models/gpt-image-2-5/run
Hunyuan Image 3
Hunyuan Image 3.0: Tencent's 80B-parameter MoE text-to-image model. High-fidelity generation with seven aspect ratio presets and a fast mode toggle.
/api/v1/models/hunyuan-image-3/run
Ideogram 4 Turbo
Fastest and cheapest Ideogram 4.0. Same stunning realism, creative designs, and text rendering: tuned for speed and iteration.
/api/v1/models/ideogram-v4-turbo/run
Ideogram 4 Balanced
The sweet spot. Balances speed, quality, and cost: a great default for most graphic design, marketing, and poster work.
/api/v1/models/ideogram-v4-balanced/run
Ideogram 4 Quality
The highest-quality Ideogram 4.0. Slowest but best for hero images, print-ready work, and detailed text-heavy layouts.
/api/v1/models/ideogram-v4-quality/run
Ideogram 4.5
Ideogram 4.5: best-in-class text rendering, posters, logos and photoreal images, plus natural-language edits and Precise Edit that changes only what you ask.
/api/v1/models/ideogram-4-5/run
ImagineArt
ImagineArt family: 1.5, 1.5 Pro, and the 2.0 preview.
/api/v1/models/imagineart/run
Kling Image
Kling Image V3. High-quality text-to-image with flexible aspect ratios.
/api/v1/models/kling-image/run
Krea Image
Krea's aesthetic text-to-image, three tiers in one tool. Turbo for fast, cheap (0.5 credit) generation; Medium and Large for higher fidelity. Every tier takes a creativity control and optional style-reference images.
/api/v1/models/krea-v2/run
Luma UNI 1
Luma UNI 1 (Standard + MAX) via Runware. Text-to-image and reference-guided image editing with one prompt, two quality tiers.
/api/v1/models/luma-uni-1/run
P-Image
Pruna P-Image. Sub-second text-to-image with optional custom dimensions.
/api/v1/models/p-image/run
P-Image Ideogram
Ideogram-class text rendering on the Pruna backbone. Pick a thinking budget from 0.1 to 1 credit per image.
/api/v1/models/p-image-ideogram/run
Pony Realism
Pony Realism - Stylized anime generation
/api/v1/models/ponyxl-ponyrealism-v23/run
Pony NAI
Pony NAI - Stylized anime generation
/api/v1/models/ponyxl-tponynai3-v7/run
Wai ANI
Wai ANI - Stylized anime generation
/api/v1/models/ponyxl-waianinsfwponyxl-v140/run
Qwen 3 Pro
Qwen Image 3.0 Pro: text-to-image generation and image editing in one model. Generate from a prompt, or supply 1-3 reference images plus an instruction.
/api/v1/models/qwen-3-pro/run
Qwen Image Plus
Fast generation with excellent quality
/api/v1/models/qwen-image-plus/run
Qwen Image Max
Highest quality output
/api/v1/models/qwen-image-max/run
Qwen Image 2.0
Fast, balanced image generation and editing
/api/v1/models/qwen-image-2.0/run
Qwen Image 2.0 Pro
Enhanced text rendering, realistic textures, and semantic adherence
/api/v1/models/qwen-image-2.0-pro/run
Recraft V4.1
Recraft's latest image model. Better photorealism, smoother gradients, and improved text rendering vs V4. ~1024px output.
/api/v1/models/recraft-v4.1/run
Recraft V4.1 Pro
V4.1 at ~2048px resolution. Print-ready and large-scale work with the same prompt accuracy and design taste as standard.
/api/v1/models/recraft-v4.1-pro/run
Recraft V4.1 SVG
Production-ready SVG vector output. Clean geometry, structured layers, editable paths: V4.1's design taste applied to vector.
/api/v1/models/recraft-v4.1-svg/run
Recraft V4.1 Pro SVG
Detailed SVG vector graphics with finer paths and more geometric detail than standard SVG.
/api/v1/models/recraft-v4.1-pro-svg/run
Riverflow
Sourceful Riverflow 2.0 (Fast + Pro) via Runware. Text-to-image with optional reference image guidance: references steer style and composition, the model generates a fresh frame from your prompt. Two quality tiers.
/api/v1/models/riverflow/run
Seedream 4.5
ByteDance Seedream 4.5: new-generation image creation with superior aesthetics, text rendering, and up to 4K resolution.
/api/v1/models/seedream-4/run
Seedream 5
Seedream 5 Pro: the flagship Seedream image model with sharper realism, stronger prompt adherence, and best-in-class text rendering.
/api/v1/models/seedream-5/runSeedream 5 Flash
Seedream 5 Flash: the fast, low-cost Seedream 5 model for quick drafts and high-volume image generation and editing.
/api/v1/models/seedream-5-flash/run
Seedream 5 Lite
ByteDance Seedream 5.0 Lite: fast, high-quality image generation and editing with strong aesthetics and text rendering.
/api/v1/models/seedream-5-lite/run
WAN 2.6 Image
Alibaba WAN 2.6 text-to-image with prompt enhancement and multi-image output.
/api/v1/models/wan-2.6-image/run
WAN 2.7 Standard
Faster Wan 2.7 image generation and editing
/api/v1/models/wan-2.7-image/run
WAN 2.7 Pro
Higher quality Wan 2.7 tier with 4K support for text-to-image
/api/v1/models/wan-2.7-image-pro/run
WAN 2.2 Image
Fast cinematic image generation (3-6 seconds) with up to 2MP output and optional LoRA support.
/api/v1/models/wan-image/run
Grok Image
xAI Grok Imagine. Fast tier for quick iteration, Quality tier for higher fidelity at 1k or 2k.
/api/v1/models/xai-image/run
Z Image Realistic
Z Image text-to-image, Realistic mode. Square / portrait / landscape compositions, 256–1536px on each side.
/api/v1/models/z-image-spicy/run
Z-Image Turbo
Super-fast 6B parameter text-to-image with great text rendering and LoRA support.
/api/v1/models/z-image-turbo/runQuestions & Answers
Frequently Asked Questions
Authentication, pricing, async jobs, and output lifetime for the PixelDojo API
Create an API key on the API Keys page (any signed-in PixelDojo account can) and send it as a Bearer token: Authorization: Bearer pd_your_api_key. The same key works on every model endpoint.
POST to /api/v1/models/{apiId}/run with the model input. You get back a jobId and a statusUrl. Poll GET /api/v1/jobs/{jobId} until the status is completed, or pass webhook_url on the run call to be notified when the job finishes. Every model publishes its JSON schema at /api/v1/models/{apiId}/schema.
Each model lists its credit cost per generation or per second on this page and in GET /api/v1/models. These are the same credits you use in the PixelDojo web app. Plans start at $10/month for 160 credits, and credit packs start at $5 for 80 credits with no subscription needed. Failed jobs are refunded automatically.
150+ image, video, and audio models, including Nano Banana, Flux 2, GPT Image 2, Seedream 5, Kling, Veo 3.1, WAN 2.7, and Seed Audio 1.0. Browse them above, or list them with GET /api/v1/models.
API outputs are available for one hour after a job completes, and every asset in the job response carries an expiresAt time. Download or copy anything you want to keep.
Yes. The OpenAPI 3.1 spec is at /api/openapi, an LLM-optimized reference is at /llm.txt, and the TypeScript SDK is @pixeldojo/sdk on npm.
Yes. Connect the hosted MCP server at https://pixeldojo.ai/mcp from Claude, Cursor, Codex, ChatGPT and other MCP clients, or run npx @pixeldojo/mcp init for a local install. See the Skills and MCP page for every tool.
Quick start:
https://pixeldojo.ai/api/v1