Cookie Preferences
We use cookies to personalize content and analyze traffic. See our Cookie Policy.
No image yet. Submit the form to generate image.
Explore different use cases and parameter configurations
Transparent pricing with no hidden fees. Pay as you go.
| Rule & Modality | Channel | Credits | Price (USD) | Official / Reference Price | Daily Savings |
|---|---|---|---|---|---|
luma-photon imageLuma | Starter | 0.4per run | $0.002 | - | - |
Complete guide to using luma-photon
Build atmospheric image generation into your product with the luma/photon API on ApiPass. Luma Photon converts text prompts into professional-quality images with strong lighting, natural composition, emotional warmth, and rich environmental detail. Submit an asynchronous task, poll for completion, and receive CDN image URLs ready for display, download, or downstream workflows.
Luma Photon is a text-to-image model designed for prompt-based visual generation. It is known for beautiful lighting, balanced compositions, warm everyday scenes, and realistic environmental details such as flour dust, steam, dust motes, soft window light, and atmospheric glow. On ApiPass, luma/photon is available through a ready-to-use REST API with asynchronous task handling, normalized CDN output URLs, optional callback notifications, and provider channel routing.
Generate images directly from natural language prompts. Describe the subject, setting, mood, lighting, texture, and composition, then use the returned resultJson.resultUrls values as production-ready image links.
Photon is especially strong for natural lighting, cozy interiors, food and bakery scenes, everyday lifestyle photography, realistic people in context, and emotionally resonant marketing visuals.
Create a task with POST /api/v1/jobs/createTask, save the returned data.taskId, then query GET /api/v1/jobs/recordInfo until the state becomes success or fail. If callBackUrl is provided, ApiPass sends a completion callback using the same response structure as the query endpoint.
Photon excels at natural light, golden hour, morning glow, soft evening lamps, and atmospheric illumination. Prompts that specify light source and quality often produce especially polished, professional-looking results.
Create images with authentic mood and lived-in feeling, from pets relaxing by the fireplace to family moments around the dinner table. Photon is well suited to lifestyle, editorial, and brand storytelling visuals.
Photon responds well to details such as steam rising from food, flour in the air, wet pavement, oil-stained walls, and ambient particles. These details help turn simple prompts into visually textured scenes.
The model produces visually pleasing layouts with realistic scene structure, making it useful for final deliverables, creative mockups, campaign images, and client-facing visual production.
Generate authentic, warm scenes of homes, families, streets, cafes, and everyday moments. Photon is a strong fit for apps that need believable lifestyle imagery without organizing a full photoshoot.
Create appetizing culinary scenes with steam, morning light, rustic shelves, artisan textures, and realistic kitchen atmosphere for menus, ads, social content, and product storytelling.
Produce cozy living rooms, kitchens, studios, reading corners, and warm indoor environments. Use prompts that specify materials, time of day, lighting, and emotional mood for stronger results.
Build product and brand visuals with natural composition and polished atmosphere. Photon is suitable for hero images, social ads, editorial-style concepts, and campaign ideation workflows.
Choose the Photon model that best fits your speed, quality, and iteration requirements.
Photon is the standard high-quality option for professional text-to-image generation. It is best for final deliverables, client-facing visuals, polished lifestyle images, and work where lighting, atmosphere, composition, and emotional realism matter most.
Photon Flash is positioned for faster, lower-cost output and is useful for high-volume generation, prototyping, and budget-sensitive workflows. Use Photon when you want stronger final quality; use a speed-optimized variant when iteration speed is the priority.
The source documentation lists Photon at $0.015 per image. Pricing shown in documentation is for reference, and the final task charge recorded by ApiPass is authoritative.
The current regular channel is configured as 7 credits per image. Billing is handled by ApiPass model credit rules, so you do not need to add any extra billing fields to the request.
Use channel: auto for automatic provider routing, or choose starter, regular, or official when you want more direct control over cost and stability tradeoffs.
Describe the scene, subject, lighting, mood, composition, and environmental details. Photon works especially well with prompts that include natural lighting, time of day, atmosphere, textures, and emotional context.
Send a POST request to https://api.apipass.dev/api/v1/jobs/createTask with model set to luma/photon and input.prompt set to your image description. You can optionally include channel and callBackUrl.
Save data.taskId from the create response, then call GET https://api.apipass.dev/api/v1/jobs/recordInfo?taskId=<APIPASS_TASK_ID> until state is success or fail. Successful tasks return generated image URLs in resultJson.resultUrls.
ApiPass returns CDN URLs rather than base64 output. Display the generated images in your app, download them, store them in your asset pipeline, or pass them into editing, upscaling, background removal, or image-to-video workflows.
All APIs require authentication via Bearer Token.
Authorization: Bearer
Submit a new Luma Photon text-to-image generation task.
The API accepts a JSON payload with the following structure:
1{
2 "model": "luma/photon",
3 "callBackUrl": "string (optional)",
4 "channel": "auto",
5 "input": {
6 "prompt": "A cinematic ocean wave at sunrise, highly detailed"
7 }
8}modelRequiredstringThe model name. For this endpoint, it must be fixed to luma/photon.
"luma/photon"
callBackUrlOptionalstringCallback URL for task completion notifications. If omitted, no callback will be sent.
"https://your-domain.com/api/callback"
channelOptionalstringOptional APIPASS provider routing setting. The default channel is auto; APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics. starter is ultra-low-cost with limited quotas and weaker stability. regular is the standard channel and is much cheaper than official APIs with moderate stability. official uses the model native API with high stability, fast task execution, and official pricing.
The default value for the channel parameter is auto. When enabled, APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics to balance minimal cost and reliable performance. starter is ultra-low-cost with limited quotas and weaker stability; regular is standard and much cheaper than official APIs with moderate stability; official uses the model native API with high stability, fast task execution, and official pricing.
Available options:
auto
The input object contains the Luma Photon generation parameters.
input.promptRequiredstringPositive text prompt used to generate the image.
The prompt cannot be empty. Describe the subject, scene, style, lighting, mood, and composition for better image generation results.
"A cinematic ocean wave at sunrise, highly detailed"
1curl --request POST \
2 --url "https://api.apipass.dev/api/v1/jobs/createTask" \
3 --header "Authorization: Bearer ${APIPASS_API_KEY}" \
4 --header "Content-Type: application/json" \
5 --data '{
6 "model": "luma/photon",
7 "channel": "auto",
8 "input": {
9 "prompt": "A cinematic ocean wave at sunrise, highly detailed"
10 }
11 }'1{
2 "code": 200,
3 "message": "success",
4 "data": {
5 "taskId": "task_xxxxxxxxxxxxxxxx"
6 }
7}codeStatus code. 200 indicates success; other values indicate failure.
messageResponse message. Provides an error description when the request fails.
data.taskIdApiPass task ID. Save this value and use it to query task status and results.
flux
flux
Generate photorealistic images with robust text
Starting from
0 credits
Nano Banana 2 Lite, aka Gemini 3.1 Flash-Lite Image, is a newly released image model from Google DeepMind built for fast 1K image generation, efficient creative iteration, prompt-based image editing, and responsive visual output in product-facing creative scenarios.
Starting from
0 credits
OpenAI
OpenAI
Generate intentionally designed visuals with less prompting using the latest OpenAI GPT Image 2 model.
Starting from
0 credits
Qwen
Qwen
Starting from
0 credits
Nano Banana now allows you to freely draw on edited images, bringing you a completely new experience. Simply click on the image to draw whatever you want. You can also add text and details, and Gemini will do the rest.
Starting from
0 credits
Fast image generation model built on Gemini 3.1 Flash Image. Supports text-to-image, image editing, multi-image fusion with up to 14 reference images, Google Search grounding, and outputs up to 4K resolution.
Starting from
0 credits
seedream
seedream
Starting from
0 credits
grok
grok
Grok Imagine is xAI’s AI video generation model for creating high-quality videos with realistic motion, native audio, and synchronized speech. Grok Imagine 1.5 introduces faster generation speeds, improved motion physics, and stronger visual consistency for modern AI video applications.
Starting from
0 credits
qwen
qwen
Generate realistic 2K images with structured text
Starting from
0 credits
seedream
seedream
Starting from
0 credits
OpenAI
OpenAI
Bring your ideas to life with sharper, faster, more precise image generation using the GPT Image 2.5 API.
Starting from
0 credits
wan
wan
Generate images with cinematic precision through high-fidelity text-to-image synthesis and structural editing.
Starting from
0 credits
seedream
seedream
Gemini said Generate images with lightning-fast efficiency and high-fidelity detail through a streamlined, lightweight architecture optimized for instant creative expression.
Starting from
0 creditsqwen
qwen
Generate realistic 2K images with structured text
Starting from
0 credits
seedream
seedream
Starting from
0 credits