> ## Documentation Index > Fetch the complete documentation index at: https://docs.budgetpixel.com/llms.txt > Use this file to discover all available pages before exploring further. # Image Generation API > Generate and edit images from your code with FLUX 3, Nano Banana 2.1, GPT Image 2.5, SeeDream 5.0, Qwen Image 3.0 and more, through one BudgetPixel API key, charged only on success. **Text + images → image.** Generate images from a prompt, edit an image with an instruction, or combine several reference images. Each model has its own endpoint, `POST /v1/images/{model}`, with the options that model supports. ## Models 32 models. Each name opens its API reference with every parameter. | Model | Maker | What it does | | - | - | - | | [FLUX 3](/api-reference/black-forest-labs/generate-image-with-flux-3)
`flux-3-image` | Black Forest Labs | Text-to-image and image editing in one model. | | [FLUX 3 Klein](/api-reference/black-forest-labs/generate-image-with-flux-3-klein)
`flux-3-image-klein` | Black Forest Labs | The fast, low-cost FLUX 3: text-to-image and image editing in one model, with up to 10 reference images (free) and five sizes from 768px to 4K. | | [FLUX 2 Pro](/api-reference/black-forest-labs/generate-image-with-flux-2-pro)
`flux-2-pro` | Black Forest Labs | Premium quality with megapixel-based resolution and seed control. | | [FLUX 2 Dev](/api-reference/black-forest-labs/generate-image-with-flux-2-dev)
`flux-2-dev` | Black Forest Labs | Next-generation FLUX quality with multi-reference image editing (up to 4 reference images) and seed control. | | [FLUX 2 Klein](/api-reference/black-forest-labs/generate-image-with-flux-2-klein)
`flux-2-klein` | Black Forest Labs | Sub-second generation with excellent prompt adherence. | | [FLUX 1.1 Pro](/api-reference/black-forest-labs/generate-image-with-flux-11-pro)
`flux-1.1-pro` | Black Forest Labs | Fast, high-quality generation with enhanced prompt adherence. | | [SeeDream 4.5](/api-reference/bytedance/generate-image-with-seedream-45)
`seedream-4.5` | ByteDance | Text-to-image, plus image editing and multi-reference composition from up to 9 reference images. | | [SeeDream 5.0 Lite](/api-reference/bytedance/generate-image-with-seedream-50-lite)
`seedream-5.0-lite` | ByteDance | Fast unified text-to-image and image editing with multi-reference composition from up to 9 reference images, 2K/3K output, and grouped sequential generation. | | [SeeDream 5.0 Pro](/api-reference/bytedance/generate-image-with-seedream-50-pro)
`seedream-5.0-pro` | ByteDance | Precise image editing with full layer control. | | [SeeDream 5.0 Flash](/api-reference/bytedance/generate-image-with-seedream-50-flash)
`seedream-5.0-flash` | ByteDance | Fast, low-cost text-to-image and image editing with multi-reference composition from up to 10 reference images and 1K/2K output, typically in under 20 seconds. | | [Qwen Image 3.0](/api-reference/alibaba/generate-image-with-qwen-image-30)
`qwen-image-3.0` | Alibaba | Unified generation and editing balancing quality and speed, with multi-image fusion from up to 3 reference images. | | [Qwen Image 3.0 Pro](/api-reference/alibaba/generate-image-with-qwen-image-30-pro)
`qwen-image-3.0-pro` | Alibaba | Professional infographics, exquisite photorealism, and stronger prompt adherence. | | [Qwen Image 2.0](/api-reference/alibaba/generate-image-with-qwen-image-20)
`qwen-image-2.0` | Alibaba | Fast unified generation and editing with strong text rendering and multi-image fusion from up to 3 reference images. | | [Qwen Image 2.0 Pro](/api-reference/alibaba/generate-image-with-qwen-image-20-pro)
`qwen-image-2.0-pro` | Alibaba | Premium generation with enhanced text rendering, fine-grained realism, and stronger semantic adherence. | | [Qwen-Image](/api-reference/alibaba/generate-image-with-qwen-image)
`qwen-image` | Alibaba | Best-in-class complex text rendering and typography. | | [Wan 2.7](/api-reference/alibaba/generate-image-with-wan-27)
`wan-2.7` | Alibaba | Image generation and editing with thinking mode, multi-reference composition from up to 9 reference images, and up to 2K output. | | [Wan 2.7 Pro](/api-reference/alibaba/generate-image-with-wan-27-pro)
`wan-2.7-pro` | Alibaba | Professional edition of Wan 2.7 with 4K output support, thinking mode, and multi-reference composition from up to 9 reference images. | | [Z-Image-Turbo](/api-reference/alibaba/generate-image-with-z-image-turbo)
`z-image-turbo` | Alibaba | Ultra-fast 6B-parameter text-to-image with only 9 inference steps. | | [Nano Banana 2.1](/api-reference/google/generate-image-with-nano-banana-21)
`nano-banana-2.1` | Google | Fast text-to-image and image editing with sharper output and cleaner in-image text than Nano Banana 2. | | [Nano Banana Pro](/api-reference/google/generate-image-with-nano-banana-pro)
`nano-banana-pro` | Google | Professional asset production with advanced reasoning, precise instruction-based editing, and multi-reference composition from up to 9 reference images. | | [Nano Banana 2](/api-reference/google/generate-image-with-nano-banana-2)
`nano-banana-2` | Google | High-efficiency text-to-image and image editing with multi-reference composition from up to 9 reference images and 0.5K-4K output. | | [Nano Banana 2 Lite](/api-reference/google/generate-image-with-nano-banana-2-lite)
`nano-banana-2-lite` | Google | Budget Nano Banana 2: fast text-to-image and image editing with multi-reference composition from up to 14 reference images. | | [Kling v3](/api-reference/kling/generate-image-with-kling-v3)
`kling-v3` | Kling | Image generation with strong prompt adherence and aesthetics. | | [Kling v3 Omni](/api-reference/kling/generate-image-with-kling-v3-omni)
`kling-v3-omni` | Kling | Unified text-to-image and image editing with multi-reference composition from up to 9 reference images and up to 4K output. | | [Muse Image 1.0](/api-reference/meta/generate-image-with-muse-image-10)
`muse-image-1.0` | Meta | Agentic image generation: the model can ground your prompt with web and image search and run code for charts, tables and text layouts before rendering (all included). | | [GPT-Image-2](/api-reference/openai/generate-image-with-gpt-image-2)
`gpt-image-2` | OpenAI | Next-generation image model with significantly improved text rendering. | | [GPT Image 2.5 Sunburst](/api-reference/openai/generate-image-with-gpt-image-25-sunburst)
`gpt-image-2.5-sunburst` | OpenAI | The most capable GPT Image model, built for premium visual work and precise, instruction-scoped edits that keep subject, composition and background intact. | | [GPT Image 2.5 Flare](/api-reference/openai/generate-image-with-gpt-image-25-flare)
`gpt-image-2.5-flare` | OpenAI | The fast, everyday GPT Image model: high-quality generation with natural text rendering and reliable edits at lower latency than Sunburst. | | [P-Image](/api-reference/pruna-ai/generate-image-with-p-image)
`p-image` | Pruna AI | An optimised Qwen-based text-to-image model generating 1-megapixel images in about a second. | | [P-Image Edit](/api-reference/pruna-ai/generate-image-with-p-image-edit)
`p-image-edit` | Pruna AI | An optimised Qwen-based image editing model taking up to 3 reference images. | | [Grok Imagine](/api-reference/xai/generate-image-with-grok-imagine)
`grok-imagine-image` | xAI | Image generation with strong aesthetics and instruction-based image editing from up to 3 reference images. | | [Grok Imagine 2.0](/api-reference/xai/generate-image-with-grok-imagine-20)
`grok-imagine-image-2` | xAI | The latest Grok image model: precise editing, infographics, ads, game assets, UI/UX mockups and storyboards. | ## How a request works 1. Send `POST /v1/images/{model}` with your prompt and options. The response returns a job `id` right away. 2. Poll [`GET /v1/images/{job_id}`](/api-reference/images/get-image-job-status) until `status` is `succeeded`. The response then holds the image URLs. [Async jobs](/concepts/async-jobs) covers job statuses and errors, and [Media inputs](/concepts/media-inputs) covers passing reference images. ## Useful options * [Several images per request](/concepts/models#multiple-images-per-request) * [Grounding](/concepts/models#grounding) and [search grounding](/concepts/models#search-grounding), for prompts about real, current things * [Transparent backgrounds](/concepts/models#transparent-backgrounds) ## Pricing Each model has its own price in credits, often by output size. [`GET /v1/models?type=image`](/api-reference/models/list-available-models) returns current prices, and [`POST /v1/cost`](/api-reference/models/estimate-the-cost-of-a-request) quotes a request before you send it. You pay only for jobs that succeed; see [Pricing & credits](/concepts/pricing-and-credits). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.