Promptus API

Paste one prompt. Get a working generation app back.

Pick a model and the dashboard writes the whole build prompt — every endpoint, every parameter, the polling loop, the gotchas. Paste it into whichever AI assistant you use.

Free credits on signup. No card. Usage-based after that.

Promptthe dashboard writes your integration
CosyFlowspublish a ComfyUI graph as an endpoint
Onekey and one balance across all of it
Open~130 checkpoints, parameters exposed
Why this is not another aggregator

What you actually get on one key

Your own ComfyUI graphs, as endpoints

Around 50 distributed CosyFlow workflows — Z-Image, Qwen Image Edit, Wan 2.2, ChronoEdit, InfiniteTalk dubbing, ACE-Step music, F5-TTS voice, background removal, upscaling — and you can publish your own.

A saved ComfyUI graph called over REST, on the same key and balance as the hosted models rather than on a separate platform.

The frontier models, same three calls

FLUX.3 video, FLUX.2, Kontext max, Veo 3.1, Seedance 2, Nano Banana Pro, Seedream 5.0 Pro, GPT-Image-2.

Swap between any of them on one line of JSON. No separate vendor contracts, no separate billing relationships, no separate SDKs.

~130 open checkpoints, parameters exposed

Juggernaut XL, DreamShaper, Pony Diffusion XL, Realistic Vision, AlbedoBase, Animagine, ICBINP and the rest of the ecosystem through AI-Horde.

Seed, steps, CFG, sampler, scheduler, denoise, VAE and checkpoint are all yours to set. Most hosted APIs decide those for you.

The roster

Everything you can call today

Live count from the dashboard, not a roadmap. Text-to-video, image-to-video, first-and-last-frame, video extend, inpainting, multi-image edit, audio-driven dubbing, music and voice.

Black Forest Labsflux
FLUX.3 Text to VideoFLUX.3 Image to Video FLUX.3 Video ContinuationFLUX.2 Text to Image FLUX.2 Multi-Image EditFLUX.1 flux-kontext-maxflux-pro-1.1-ultra
CosyFlowsyour comfyui, distributed
Z-Image & Z-Image TurboWan 2.2 · Wan 2.1 Qwen Image Edit 2509 / 2511Flux.2 Klein 4BFlux Kontext Dev OmniGen2HiDream E1.1ChronoEdit 14B InfiniteTalk dubbingRMBG background removalGAN video upscaler Multi-angle character sheets
Googlegenai bridge
Veo 3.1 Text to VideoVeo 3.1 First & Last Frame Veo 3.1 Reference ImagesVeo 3.0 Nano Banana Pro · Gemini 3 Pro Image Nano Banana 2 · Gemini 3.1Nano Banana 2.5 FlashGemini Flash Edit
ByteDanceseedream · seedance
Seedance 2 Text to VideoSeedance 2 Audio to Video Seedance 2 Multimodal EditSeedance 2 ExtendSeedance Pro Seedream 5.0 ProSeedream 5.0Seedream 4.5Seedream 4.0
Lumadream machine
Text to VideoImage to Video · first frame· last frame · first and lastExtendReverse-Extend
Omnihumandreamactor
Audio + Image to VideoText + Audio + Image to Video Image + Video to VideoMulti-Image + Video
Music & voicesuno · ace-step · f5
Suno Chirp · vocalSuno Chirp · instrumental ACE-Step 1.5ACE-Step v1 Text to SongStable Audio 1.0 F5-TTS voice
OpenAIimage
GPT-Image-2GPT-Image-1.5GPT-Image-1 Inpainting · alpha + maskMulti-image to image
AI-Horde~130 open checkpoints
Juggernaut XLDreamShaper & DreamShaper XLPony Diffusion XL Realistic VisionAlbedoBase XLAnimagine XLICBINP Deliberate 3.0AbsoluteRealityCyberRealistic Pony Analog Madness+ 120 more

Live roster from the dashboard. Availability and per-call cost are shown against each model before you call it.

For agents and vibe-coders

Describe the app. Paste one prompt. Ship it.

Pick a model in the dashboard and it writes you a complete build prompt — every endpoint, every parameter, the polling loop, the three image-format cases, the known gotchas. Paste it into whichever assistant you use — ChatGPT, Claude, Gemini, Copilot, Cursor — and you get a working studio app back. No SDK to learn and no docs to read first.

generate · poll · retrieve
# 1 — submit
curl -X POST https://api.promptus.ai/api/generate \
  -H "Authorization: Bearer $PROMPTUS_API_KEY" \
  -d '{
    "prompt": {
      "cosyflow": "(cosy) Z-Image: Text to Image",
      "text_0": "neon alley, rain, 35mm",
      "width": 1024, "height": 1024, "steps": 25
    },
    "accountNo": "$PROMPTUS_ACCOUNT"
  }'
# -> { "uid": "job_abc123", "error": null }

# 2 — poll every 2s
GET /api/generate/progress?uid=job_abc123
# -> { "progress": 100, "output": [{ "uid": "out_xyz" }] }

# 3 — retrieve
GET /api/generate/output/job_abc123/out_xyz

Same three calls for every model

Submit, poll, retrieve. Switching from Z-Image to Veo 3.1 is a change of one string — not a new integration.

Parameters exposed, not hidden

Seed, steps, CFG, sampler, scheduler, denoise, VAE and checkpoint are all yours to set. Most hosted APIs decide these for you.

Credits, not seats

One balance spends across every provider. No per-model subscription, no minimum, no seat licence.

Pricing

One credit balance, spent wherever you like

PlanCreditsBest for
FreeIncluded on signup Testing a model, prototyping an agent tool
Pay as you goTop up any amount Production apps — a Veo 3.1 call and a Z-Image call cost different amounts, and you only pay the difference
VolumeCommitted, discounted Platforms embedding generation at scale, and white-label partners

Per-call cost varies by model, resolution and duration — a 10-second Veo 3.1 video is not priced like a 1024×1024 Z-Image. Live rates are shown per model in the dashboard before you call.

Questions

Straight answers

Do I need to know ComfyUI?

No. Call a CosyFlow by name like any other model. Knowing ComfyUI just means you can publish your own graphs as endpoints too.

How is this different from Replicate or fal?

Replicate and fal host open models and can run ComfyUI graphs; the closed labs host their own. What is different here is the union on one key and one balance — graphs you publish, the hosted frontier models, and ~130 open checkpoints — plus a dashboard that writes the integration for you. If you only need one of those three, they are fine choices.

What about content restrictions?

Each provider keeps its own policy — a call to a hosted model is subject to that model's filter. Open checkpoints do not add one. Illegal material is prohibited on every route regardless.

Can I white-label this?

Yes, on the volume plan. That is a conversation, not a checkbox — talk to us.

Is it the same account as my Promptus app?

Yes. One login, one credit balance across the desktop app, the web app and the API.

One key. Every model you need. Free credits to start.

Generate your first image in about two minutes — or paste one prompt into your AI assistant and have it build you the whole app.

Get an API key