Skip to main content

Know what creative AI actually costs.

A hand-checked pricing reference, a workflow library, and a set of agent skills for image, video, voice, and music tools.

38 tools tracked1,800 live price rows$1.1M in free credits
live
Midjourney

Midjourney

from $10/mo

Runway

Runway

from $15/mo

ElevenLabs

ElevenLabs

from $5/mo

S

Suno

from $10/mo

Freepik

Freepik

from $25/mo

Magnific

Magnific

from $39/mo

Leonardo

Leonardo

from $12/mo

GPT Image 2

GPT Image 2

$0.05/gen

An advisor that
knows the prices

Ask how to make something for a budget. Every answer is grounded in Scopeful's pricing data and tracks what the run would actually cost. Click a prompt to watch it answer.

Every recommendation reads from the same pricing data the calculator uses. The advisor never guesses a number, it pulls the live USD-per-generation cost for the exact model and resolution you asked about.

Ask for a 30-second video or a batch of 100 images and the advisor sums what it would actually cost up front. The figure updates as you change the budget, the tool, or the volume.

The scene runs live. Pick one of the example questions and the advisor responds in place with a real, priced recommendation. No sign-up, no setup.

Featured

Skill

Scopeful Agent — The Creative AI Agent That Learns

Multi-provider workflows spanning Flux, Kling, Runway, and ElevenLabs in one execution. Persistent memory, gallery, BYOK, and MCP bridge pre-installed.

Get it

Credit vault

Stack free tiers and startup grants

Anthropic logo

Anthropic

$1k–$25k Claude API credits

$5,000
Runway logo

Runway

500K API credits · Tier 5

$5,000
ElevenLabs logo

ElevenLabs

33M chars · 12 months

$4,000
OpenAI logo

OpenAI

$1,000 API credits · 12 months

$1,000
New chat

Advisor

Ask about AI tool pricing, compare options, or write prompts for Seedance, NanoBanana, and more. Drop an image to use as a reference.

Skills your coding
agent can read

Installable knowledge packs, system prompts, skills.md files, and references that drop into Claude Code, Cursor, or any agent that reads them.

Each brain is a markdown file your agent reads at session start. Drop it in .claude/skills/ and the agent knows the tool's API, model pricing, and prompt patterns without you writing instructions.

Agents read these files automatically from the project directory. No plugin installs, no extension stores, no config. One file in the right folder, your agent has the skill on every session.

A piped curl command downloads the brain and writes it to the right folder. Run it once and the skill persists across all future sessions. No npm, no homebrew, no setup steps.

ComfyUI MCP with a
self-updating brain

Describe what you want in Claude Code and the graph builds itself inside ComfyUI. A knowledge base of nodes, models, and proven graphs keeps itself current, you never maintain it.

A manifest of every custom node and model in the ComfyUI ecosystem, refreshed on each install. Your agent queries it to know which nodes exist, what inputs they take, and which models are compatible with each other.

Type 'upscale this image 4x with a detail-preserving model' and the agent selects the right node, connects it to a model loader, and wires the output. The graph builds itself from what you describe.

Synced from the ComfyUI manager registry at install time. When a node updates or a new model drops, your agent sees it on the next session. No manual reference list to maintain.

KSampler

current

VAE Decode

current

Upscale (4x)

current

ControlNet

current

comfyui mcp knowledge base synced

Watch: a prompt in Claude Code builds the graph inside ComfyUI

demo video
412 nodes · 38 graphs auto-updates

Try Scopeful in
your browser

Available for Midjourney, Runway, and 3 more. Click the Scopeful badge in any prompt field to optimize on the spot — no setup, no sign-in to use the prompt rewrite.

Select a prompt on Midjourney or Runway and press Ctrl+Shift+O. The extension restructures it for better output, fixing weak framing and adding specificity without leaving the tool's page.

A quality meter runs on every prompt you type. Scores below 70 get inline suggestions for what to add: more detail, stronger action verbs, or specific style references.

Prompts save per tool with tags. Each run logs the model used, credits spent, and output quality so you can compare what worked across iterations.

midjourney.com/imagine
Scopeful
/imagine studio product shot, nice light, ceramic mug41
Stronger prompt

soft window light, 85mm, matte ceramic mug, shallow depth of field

saved to your library14 runs · $0.58 this session

One MCP server,
every AI creative tool

Your agent queries Scopeful MCP for live pricing, installable skills, and ready-to-use prompts. No more guessing what an image costs or how to talk to a tool.

Your agent calls a single tool to get USD-per-generation for any model, at any resolution, at any volume. The same data the calculator reads, returned as JSON it can use directly.

Drop a skills.md into Claude Code or Cursor and the agent knows the tool's API, model lineup, and prompt patterns. Twelve published skills cover the most common creative tools.

Eight production-tested system prompts for image, video, voice, and music tools. Copy the prompt, paste it into your agent, and the run lands the brief on the first try.

Live pricing

1,800 rows

Installable skills

12 published

Ready prompts

8 templates

scopeful mcp live

agent › scopeful mcp

cheapest 1K image at 500/mo?

scopeful mcp › 3 results

1. OpenAI gpt-image-1 · $5/mo · 500 imgs

2. Midjourney Standard · $10/mo · 500 imgs

3. Freepik · $25/mo · 500 imgs

install: npx add @scopeful/mcp

Credits, stacked
in one vault

A curated, hand-verified vault of free tiers and startup grants from AI platforms, over $1.1M across 26 programs. Filter by what you qualify for and claim straight from the table.

26 verified programs from ComfyUI, Runway, ElevenLabs, and more. Each entry documents the application process, eligibility rules, and how to claim. Total value: $1.1M in free credits.

Set your company stage, team size, and country. The vault shows only programs you qualify for. A solo founder in the UK sees a different list than a 50-person US startup.

Every program is hand verified. Expired grants are removed within 48 hours. Dead links and outdated eligibility rules do not make it through to the vault.

$1,127,161+ across 26 programs
ElevenLabs logo

ElevenLabs

Startup grant

$4,000

33M chars · 12 months

Under 25 employees · valid business email · display Grants logo for 12 months

Claim
Anthropic logo

Anthropic

Startup grant

$5,000

$1k–$25k Claude API credits

Early-stage startup · Partner/Premium needs VC or accelerator referral

Claim
OpenAI logo

OpenAI

Researcher

$1,000

$1,000 API credits · 12 months

Researchers studying responsible deployment, safety, or societal impact

Claim
Runway logo

Runway

Startup grant

$5,000

500K API credits · Tier 5

Seed to Series C startups building on Runway APIs

Claim
Runway logo

Runway

Creator program

$3,000

Unlimited plan + ~1M credits

Hand-picked from portfolio + socials. Apply rolling.

Claim
Google AI Studio logo

Google AI Studio

Individual

$300

Cloud credits · 90 days

New Google Cloud accounts. Card required, not charged.

Claim
Showing 6 of 26 programsCurated and verified. Not auto-scraped.

Workflows for
node-based tools

A library of ready workflows for ComfyUI, Magnific, and other node systems. Each one links out to build, with a system prompt written for every node.

Every workflow has a direct link to ComfyUI, Magnific, or the target platform. Click it and the graph loads ready to run. No file downloads, no import steps.

Each node in the workflow has a written system prompt explaining what it does and how it fits. Read it before you run to understand the intent behind every connection and setting.

Built for visual programming environments where nodes connect to form a pipeline. ComfyUI for image workflows, Magnific for upscaling. Each one is a complete pipeline, not a single node.

The cheapest way to run your workload

Pick a model, pick a quantity, and Scopeful ranks every plan and pay-as-you-go option in dollars. No spreadsheet required.

preview

Model

GPT Image 2GPT Image 2

Quantity

1,000 / mo@ 1K

Resolution

1K

Access

UI
Same engine that ranks the live calculator. Preview: 1,000 GPT Image 2 images / month at 1K, via UI.
Cheapest way to run 1,000 GPT Image 2 / moranked
Toolmonthly · per image
Adobe FireflyAdobe Fireflybest$50.00/mo$0.05 per image
RunwayRunway$95.00/mo$0.09 per image
Krea AIKrea AI$105.00/mo$0.11 per image
ReplicateReplicate$180.00/mo$0.18 per image
Open the live calculatorSame engine · real data · live results
Deals & challenges

Promo codes, trials, and contests

Challenge

Reve 2.0 image contest: submit your best 10 images in one week. Three winners share $175K ($100K / $50K / $25K), with featured placement for the winners. Free to enter; open to anyone 18+ with a Reve account.

$175K prize pool

prize pool

Enter
From the app

Skills, workflows, and notes

Drop-in agent skills, ready workflows for ComfyUI and Magnific, and short notes from the app. Everything here is free to read on app.scopeful.org.

Free account, full access.

Compare real prices, save your workloads, and track cost history. No subscription needed.