AI infrastructure for your tech stack
A suite of custom small models plugged into the right infrastructure to power your AI applications
const searchResults = await jigsaw.web.search({
query: "What is the weather in San Francisco?"
})
const structuredOCR = await jigsaw.vision.vocr({
url: "https://jigsawstack.com/preview/vocr-example.jpg",
prompt: ["total_price", "tax", "highlighted_item_name"]
})
const aiScrapedData = await jigsaw.web.ai_scrape({
url: "https://news.ycombinator.com/show",
element_prompts: ["post title", "post points"]
})
const audioFile = await jigsaw.audio.text_to_speech({
text: "Hello, world!"
})
const translatedText = await jigsaw.translate({
text: ["Hey, how are you?"],
target_language: "zh"
})
Integrate in seconds on any platform
Easy to use REST APIs that work out of the box in every language and framework with fully managed caching, logging and authentication
javascript
python
php
ruby
go
java
swift
dart
kotlin
csharp
curl
import { JigsawStack } from "jigsawstack";
const jigsaw = JigsawStack({
apiKey: "sk39wo393.....32ncsmw9339RNj3"
});
const response = await jigsaw.web.search({
"prompt": "What are the best food places to visit in San Francisco?"
})$
npm i jigsawstack
First class Developer Experience (DX)
Striking the right balance between code and dashboard
Logging and analytics on all APIs
Access real-time logs and analytics on all your APIs. Debug errors, track users, location maps, sessions, countries, IPs and 30+ data points
API key security control
Fine grained control over API keys. Whitelist domains with flexible wildcard support, set expiration date and limit access to specific APIs with unlimited keys
Fully typed SDKs
The best docs are the kind that you don't need. Fully typed SDKs with auto-completion and self explanatory params
Team and project management
Manage multiple projects and teams with access control. Invite unlimited team members and assign roles
Globally distributed models in 99+ locations
Access model APIs at blazing fast speeds on the edge network
Blazing fast
99.5% uptime with APIs latency reaching as low as 200ms globally
Simple scalable pricing
Scale up and down as you need without worrying about abused cost with usage based pricing
Consistency
Consistent request and response structure across all API services for predictable use
Up to date
Consistent training for all JigsawStack models to ensure the latest technology is always available without breaking changes
Built-in integrations
Work with your favorite frameworks
Available
Groq
Fastest LLM inference
Available
LangChain
LLM orchestration & tooling
Available
Zapier
No-code custom zaps
Coming soon
Vercel
Access all APIs from Vercel
Coming soon
Supabase
Access all APIs from Supabase
