>_
Use in Your Local AI Tools
Pick useful capabilities from SandBase, run Setup once, and use them in Codex, Claude, Cursor, or Kiro.
$ curl -fsSL https://sandbase.ai/install.sh | shSandBase
for the Real World.
Bring AI models, real-world APIs and reusable Skills into the work your Agent needs to do. Find a capability in the catalog, connect it through SandBase, and build a workflow that can research a topic, process files or turn a request into a usable result.
MODEL DISCOUNTS
Production-Ready Models for
Building Reliable AI Workflows.
- 01
openai/gpt-image-2/editImage edit45%OFFBASE$0.20$0.11USD / request - 02openai/gpt-image-2Image45%OFFBASE
$0.20$0.11USD / request - 03openai/gpt-6-solLanguage35%OFFBASE
$2.00$1.30Output $6.50USD / 1M tokens - 04
google/nano-banana-2/editImage edit35%OFFBASE$0.06$0.039USD / request - 05google/nano-banana-2Image35%OFFBASE
$0.06$0.039USD / request - 06google/nano-banana-pro/editImage edit35%OFFBASE
$0.12$0.078USD / request - 07openai/gpt-6-astraLanguage35%OFFBASE
$10.00$6.50Output $32.50USD / 1M tokens - 08google/nano-banana-proImage35%OFFBASE
$0.12$0.078USD / request - 09
anthropic/claude-opus-5.5Language25%OFFBASE$4.00$3.00Output $15.00USD / 1M tokens - 10
kwaivgi/kling-video/v2.6/standard/motion-controlVideo15%OFFBASE$0.35$0.2975USD / request - 11kwaivgi/kling-video/v2.6/pro/motion-controlVideo15%OFFBASE
$0.70$0.595USD / request
Catalog snapshot · example prices and discounts; confirm current availability and pricing on the live model page.
GET STARTED
Three Ways to Put It to Work.
Use it in your local AI tools, call it from your app, or build a reusable Agent. One key covers all three.
{ }
Call an API
Copy a working request for a Model, search, scraping, data, or SaaS API — the price is on the card.
↗
Build an Agent
Define the job, give it tools, test it, then publish or schedule it.
Build an AgentTHE STORE
Every Capability Has a Price.
419 models & variants and 965 API endpoints in the Oct 10, 2026 snapshot. Confirm current prices and request schemas on each live page.
Discovers, validates, and prioritizes keywords with DataForSEO.
Runs on usageEfficiency-optimized MoE with a 1M-token context window.
$0.14 in · $0.28 out / 1MState-of-the-art image generation and editing.
$0.06 / callNeural web search with page contents returned inline.
$0.007 / callReasoning, coding, and tool use for long-running workflows.
$5 in · $25 out / 1MExtract transcripts and captions for research and summaries.
Free to cloneProfiles, posts, reels, and comments for creator research.
View pricing / endpointResearch videos, channels, and audiences from your AI tools.
Public SkillONE CAPABILITY
Call One Capability
from Your Product.
Use a capability directly. Reuse it inside an Agent when the work grows.
01ModelsAdd reasoning, vision, audio, image, and embedding models.
02Search APIsLet your Agent search the live web and return sources.
03Data extractionTurn webpages and files into clean data your Agent can use.
04SaaS APIsConnect to business systems, social data, and workflow tools.
05Agent templatesStart from working examples and adapt them to your use case.
06SkillsReuse packaged instructions and code inside Agent workflows.
AGENT WORKFLOWS
Turn a Question into
Finished Work.
Research, enrich, and deliver a source-backed brief from one reusable workflow.
01 / INPUT
Business Question
Research a company
Set the scope
List the questions
02 / PROCESS
Research Agent
Search live sources
Add company data
Build the brief
03 / OUTPUT
Deliverable
Customer brief
Sources cited
Ready to share
BUILD AN AGENT
Define It, Test It, Deliver It.
Give the job a shape, watch one run before anything depends on it, then hand it to an AI tool, an API, or a schedule.
Build an Agent01
Define
Define the job and give the Agent the right capabilities.
02
Test a Run
See the result before anything depends on it.
03
Deliver
Deliver it to an AI tool, an API, or a schedule.
ACTIVITIES
Every Run Leaves a Record.
Each execution becomes a run with its input, output, trace, and status — and Activities shows what it cost.
Input & output
The request that started it. The result it delivered.
Trace & status
Every step along the way, kept with the run.
Usage & cost
Activities shows what each execution cost.
PRICING
Pay for What You Run.
FAQ
Choose Your Way In.
Setup puts tools inside your AI app. APIs let your product call one tool directly. Build Agent is for reusable, multi-step work.
Who is SandBase for?+
SandBase is for builders who need working AI capabilities quickly, and FDEs who need to turn customer requirements into reusable agent workflows.
Should I start with Setup, APIs, or Build Agent?+
Use Setup when you want tools inside Codex, Claude, Cursor, or Kiro. Use APIs when your product needs one tool. Use Build Agent when the job has multiple steps and should be reused.
What is in the Store?+
The Store is where you find reusable agent capabilities: models, APIs, ready-made agents, and skills. You can test them, copy them, install them into Setup, or clone them into Build Agent.
What is an agent workflow?+
An agent workflow is a reusable job with instructions and tools. It can research a customer, enrich leads, monitor competitors, or run another repeatable process.
What happens after I build an agent?+
You can test it, publish it so apps and AI tools can call it, or schedule it to run automatically. Every execution becomes a run with input, output, trace, and status.
What are webhooks for?+
Webhooks notify your system when async model, API, or agent work finishes or fails, so nothing has to poll for the result.