mystic.ai Open in urlscan Pro
34.95.76.235  Public Scan

Form analysis
0 forms found in the DOM

Text Content

Looking to run AI models on your cloud or on-prem? Check out Enterprise

 * Enterprise
 * About
 * Pricing
 * Discord

 * Explore AI models
 * Explore
 * Log in
   Sign up / Log in
 * 


RUN ANY AI MODEL AS AN APIWITHIN SECONDS

Low latency serverless API to run and deploy ML models

STABILITYAI/STABLE-DIFFUSION-XL-REFINER-1.0

SD-XL 1.0-base

Updated 3 months ago3 months ago

181.25K Runs



PAULH/OPEN-JOURNEY-XL

OpenJourney XL. A finetuned SDXL on the Midjourney v5 dataset

Updated 2 months ago2 months ago

43.29K Runs



META/LLAMA2-7B-CHAT

Llama 2 13B for chat applications with vLLM

Updated about 2 months agoabout 2 months ago

20.63K Runs



META/CODELLAMA-13B-INSTRUCT

CodeLlama 13B instruct

Updated 28 days ago28 days ago

18.69K Runs



AINZOIL/SD-XL

SD-XL with more parameters (new: Batch, Seeds)

Updated about 1 month agoabout 1 month ago

8.5K Runs



AINZOIL/DREAMSHAPER_8

trust me you'll get mind blown with this one ;)

Updated 2 months ago2 months ago

7.39K Runs



META/LLAMA2-13B-CHAT



Updated about 2 months agoabout 2 months ago

3.81K Runs



AINZOIL/ANIMAGINE-XL

if you want some anime waifu but with the power of xl

Updated 2 months ago2 months ago

3.3K Runs



STABILITYAI/SDXL-IMG2IMG

SDXL based img2img

Updated about 1 month agoabout 1 month ago

1.49K Runs



MISTRALAI/MISTRAL-7B-CHAT-V0.1

A 7B LLM by Mistral (chat)

Updated about 2 months agoabout 2 months ago

1.48K Runs



MISTRALAI/MISTRAL-7B-INSTRUCT-V0.1

A 7B LLM by Mistral (instruct)

Updated about 2 months agoabout 2 months ago

962 Runs



RUNWAYML/STABLE-DIFFUSION-V1-5

Stable Diffusion v1.5 for text->image

Updated 3 months ago3 months ago

949 Runs



MATTHEW/E5_LARGE-V2

Embedding model by Microsoft

Updated 2 months ago2 months ago

515 Runs



PAULH/WAIFU-DIFFUSION

A waifu just for you

Updated 3 months ago3 months ago

465 Runs



PAULH/BLIP-2

Blip 2 from Salesforce (image -> text)

Updated 2 months ago2 months ago

381 Runs



META/CODELLAMA-34B-INSTRUCT



Updated about 2 months agoabout 2 months ago

346 Runs

AINZOIL/DREAMSHAPER_8

trust me you'll get mind blown with this one ;)

Updated 2 months ago2 months ago

7.39K Runs



META/LLAMA2-13B-CHAT



Updated about 2 months agoabout 2 months ago

3.81K Runs



AINZOIL/ANIMAGINE-XL

if you want some anime waifu but with the power of xl

Updated 2 months ago2 months ago

3.3K Runs



STABILITYAI/SDXL-IMG2IMG

SDXL based img2img

Updated about 1 month agoabout 1 month ago

1.49K Runs



MISTRALAI/MISTRAL-7B-CHAT-V0.1

A 7B LLM by Mistral (chat)

Updated about 2 months agoabout 2 months ago

1.48K Runs



MISTRALAI/MISTRAL-7B-INSTRUCT-V0.1

A 7B LLM by Mistral (instruct)

Updated about 2 months agoabout 2 months ago

962 Runs



RUNWAYML/STABLE-DIFFUSION-V1-5

Stable Diffusion v1.5 for text->image

Updated 3 months ago3 months ago

949 Runs



MATTHEW/E5_LARGE-V2

Embedding model by Microsoft

Updated 2 months ago2 months ago

515 Runs



PAULH/WAIFU-DIFFUSION

A waifu just for you

Updated 3 months ago3 months ago

465 Runs



PAULH/BLIP-2

Blip 2 from Salesforce (image -> text)

Updated 2 months ago2 months ago

381 Runs



META/CODELLAMA-34B-INSTRUCT



Updated about 2 months agoabout 2 months ago

346 Runs



STABILITYAI/STABLE-DIFFUSION-XL-REFINER-1.0

SD-XL 1.0-base

Updated 3 months ago3 months ago

181.25K Runs



PAULH/OPEN-JOURNEY-XL

OpenJourney XL. A finetuned SDXL on the Midjourney v5 dataset

Updated 2 months ago2 months ago

43.29K Runs



META/LLAMA2-7B-CHAT

Llama 2 13B for chat applications with vLLM

Updated about 2 months agoabout 2 months ago

20.63K Runs



META/CODELLAMA-13B-INSTRUCT

CodeLlama 13B instruct

Updated 28 days ago28 days ago

18.69K Runs



AINZOIL/SD-XL

SD-XL with more parameters (new: Batch, Seeds)

Updated about 1 month agoabout 1 month ago

8.5K Runs

MISTRALAI/MISTRAL-7B-INSTRUCT-V0.1

A 7B LLM by Mistral (instruct)

Updated about 2 months agoabout 2 months ago

962 Runs



RUNWAYML/STABLE-DIFFUSION-V1-5

Stable Diffusion v1.5 for text->image

Updated 3 months ago3 months ago

949 Runs



MATTHEW/E5_LARGE-V2

Embedding model by Microsoft

Updated 2 months ago2 months ago

515 Runs



PAULH/WAIFU-DIFFUSION

A waifu just for you

Updated 3 months ago3 months ago

465 Runs



PAULH/BLIP-2

Blip 2 from Salesforce (image -> text)

Updated 2 months ago2 months ago

381 Runs



META/CODELLAMA-34B-INSTRUCT



Updated about 2 months agoabout 2 months ago

346 Runs



STABILITYAI/STABLE-DIFFUSION-XL-REFINER-1.0

SD-XL 1.0-base

Updated 3 months ago3 months ago

181.25K Runs



PAULH/OPEN-JOURNEY-XL

OpenJourney XL. A finetuned SDXL on the Midjourney v5 dataset

Updated 2 months ago2 months ago

43.29K Runs



META/LLAMA2-7B-CHAT

Llama 2 13B for chat applications with vLLM

Updated about 2 months agoabout 2 months ago

20.63K Runs



META/CODELLAMA-13B-INSTRUCT

CodeLlama 13B instruct

Updated 28 days ago28 days ago

18.69K Runs



AINZOIL/SD-XL

SD-XL with more parameters (new: Batch, Seeds)

Updated about 1 month agoabout 1 month ago

8.5K Runs



AINZOIL/DREAMSHAPER_8

trust me you'll get mind blown with this one ;)

Updated 2 months ago2 months ago

7.39K Runs



META/LLAMA2-13B-CHAT



Updated about 2 months agoabout 2 months ago

3.81K Runs



AINZOIL/ANIMAGINE-XL

if you want some anime waifu but with the power of xl

Updated 2 months ago2 months ago

3.3K Runs



STABILITYAI/SDXL-IMG2IMG

SDXL based img2img

Updated about 1 month agoabout 1 month ago

1.49K Runs



MISTRALAI/MISTRAL-7B-CHAT-V0.1

A 7B LLM by Mistral (chat)

Updated about 2 months agoabout 2 months ago

1.48K Runs

 * company: SensusFuturis

 * company: Seelab

 * company: Vellum

 * company: Renovate AI

 * company: Charisma AI

 * company: Hypotenuse AI

 * Company: Vellum

 * Company: Charisma AI

 * Company: Hypotenuse AI

 * Company: SensusFuturis

 * Company: Seelab

 * Company: Renovate AI


OUR PRODUCT IS CRAFTED THROUGH MILLIONS OF ML RUNS

5,000+

Developers using our API



9,000+

AI models deployed


THE EASIEST WAY TO GET AN API
ENDPOINT FROM ANY ML MODEL

All the infrastructure required to run AI models with a simple API call

curl -X POST 'https://www.mystic.ai/v3/runs'
  -H 'Authorization: Bearer YOUR_TOKEN'
  -H 'Content-Type: application/json'
  -d '{"pipeline_id_or_pointer": "meta/llama2-70B-chat:latest", "input_data": [{"type":"string","value":"Hello World!"}]}'


 * ONLY PAY FOR INFERENCE TIME
   
   Pay per second with serverless pricing on our shared cluster. Pay only for
   the inference you use.
   
   


 * INFERENCE WITHIN 0.035S
   
   Within a few milliseconds our scheduler decides the optimal strategy of
   queuing, routing and scaling.
   
   


 * API FIRST AND PYTHON LOVERS
   
   RESTful API to call your model from anywhere. Python SDK to upload your own
   models.
   
   


RUN AND DEPLOY ML MODELS WITH SPEED, SCALE AND HIGH-THROUGHPUT

Our ingredients for reliable and scalable ML infrastructure


 * NO DOCKER, NO KUBERNETES, NO DEVOPS.
   
   
   USE THE TOOLS YOU ARE FAMILIAR WITH. YOU ONLY NEED TO INTERACT WITH OUR API
   AND PYTHON SDK TO RUN AI.


 * P75 SYSTEM LATENCY OF 35MS
   
   
   WITH 35MS AND 75MS OF P75 AND P95 SYSTEM LATENCY, RESPECTIVELY. EXPERIENCE
   LOW-LATENCY INFERENCE.


 * DYNAMIC SCALING
   
   
   WE DYNAMICALLY SCALE UP AND DOWN RESOURCES AS THE NUMBER OF REQUESTS FOR YOUR
   MODEL VARIES.


 * COLD STARTS REDUCTION
   
   
   OUR SMART SYSTEM WITH PREEMPTIVE AND MULTI-GPU CACHING HELPS US REDUCE
   FREQUENCY OF COLD STARTS.


 * INTELLIGENT ROUTING
   
   
   THE MOST OPTIMAL RESOURCE FOR YOUR REQUESTS IS SELECTED VIA SEVERAL RUNTIME
   METRICS RECORDED OVERTIME.


 * CI/CD, ALERTING AND MONITORING
   
   
   INTEGRATE AI IN YOUR CI/CD WORKFLOW, SET-UP ALERTS AND MONITOR YOUR
   DEPLOYMENTS WITH EASE.


 * PIPELINE AND MODEL VERSIONING
   
   
   CREATE A NEW NAMED VERSION EACH TIME YOU UPLOAD A NEW PIPELINE. KEEP TRACK OF
   ALL DEPLOYED PIPELINES AND MODELS.


 * GPU SHARING & FRACTIONALIZATION
   
   
   OUR SYSTEM AUTOMATICALLY CACHES MULTIPLE MODELS UNDER SAME GPU TO INCREASE
   EFFICIENCY AND REDUCE COSTS.


 * MULTI GPU BASED INFERENCE
   
   
   SEAMLESSLY RUN VERY LARGE MODELS IN MULTI GPU ENVIRONMENTS TO FIT THE MEMORY
   REQUIREMENTS.


 * NO DOCKER, NO KUBERNETES, NO DEVOPS.
   
   
   USE THE TOOLS YOU ARE FAMILIAR WITH. YOU ONLY NEED TO INTERACT WITH OUR API
   AND PYTHON SDK TO RUN AI.


 * P75 SYSTEM LATENCY OF 35MS
   
   
   WITH 35MS AND 75MS OF P75 AND P95 SYSTEM LATENCY, RESPECTIVELY. EXPERIENCE
   LOW-LATENCY INFERENCE.


 * DYNAMIC SCALING
   
   
   WE DYNAMICALLY SCALE UP AND DOWN RESOURCES AS THE NUMBER OF REQUESTS FOR YOUR
   MODEL VARIES.


 * COLD STARTS REDUCTION
   
   
   OUR SMART SYSTEM WITH PREEMPTIVE AND MULTI-GPU CACHING HELPS US REDUCE
   FREQUENCY OF COLD STARTS.


 * INTELLIGENT ROUTING
   
   
   THE MOST OPTIMAL RESOURCE FOR YOUR REQUESTS IS SELECTED VIA SEVERAL RUNTIME
   METRICS RECORDED OVERTIME.


 * CI/CD, ALERTING AND MONITORING
   
   
   INTEGRATE AI IN YOUR CI/CD WORKFLOW, SET-UP ALERTS AND MONITOR YOUR
   DEPLOYMENTS WITH EASE.


 * PIPELINE AND MODEL VERSIONING
   
   
   CREATE A NEW NAMED VERSION EACH TIME YOU UPLOAD A NEW PIPELINE. KEEP TRACK OF
   ALL DEPLOYED PIPELINES AND MODELS.


 * GPU SHARING & FRACTIONALIZATION
   
   
   OUR SYSTEM AUTOMATICALLY CACHES MULTIPLE MODELS UNDER SAME GPU TO INCREASE
   EFFICIENCY AND REDUCE COSTS.


 * MULTI GPU BASED INFERENCE
   
   
   SEAMLESSLY RUN VERY LARGE MODELS IN MULTI GPU ENVIRONMENTS TO FIT THE MEMORY
   REQUIREMENTS.

   
   
   
   


HOW TO GET STARTED

Run any model built by the community, dive into one of our
tutorials, or start uploading your own models.


Beginner friendly


EXPLORE AI MODELS BUILT BY THE COMMUNITY

Our community uploads AI models and makes them available for everyone to use.
They are ready to try and use as an API.

Explore AI models

STABILITYAI/STABLE-DIFFUSION-XL-REFINER-1.0

SD-XL 1.0-base

Updated 3 months ago3 months ago

181.25K Runs



PAULH/OPEN-JOURNEY-XL

OpenJourney XL. A finetuned SDXL on the Midjourney v5 dataset

Updated 2 months ago2 months ago

43.29K Runs



META/LLAMA2-7B-CHAT

Llama 2 13B for chat applications with vLLM

Updated about 2 months agoabout 2 months ago

20.63K Runs

Intermediate


TUTORIALS AND EXAMPLES OF WHAT YOU CAN BUILD ON MYSTIC

 * Llama 2 with vLLM (7B, 13B & multi-gpu 70B)

 * Build your own fast chatbot with Llama 2 and vLLM

 * Mistral AI 7B inference with vLLM

View docs

Intermediate


UPLOAD YOUR OWN AI PIPELINE

A pipeline contains all the code required to run your AI model as an endpoint.
You can define the inputs to the endpoint, any pre-processing code, the
inference pass, post-processing code and outputs to be returned back from the
endpoint.

Learn how to leverage our cold-start optimizations, createcustom environments,
enable debugging mode & logging, load model from file, and much more.

View docs

...

@pipe
def foo(bar: str) -> str:
    return f"Input string: {bar}"

with Pipeline() as builder:
    bar = Variable(str)
    output_1 = foo(bar)

    builder.output(output_1)

my_pipeline = builder.get_pipeline()
my_pipeline.run("test")

...


PAY PER SECOND

Start from as little as $0.1/h

$50 free credits every month

Run your models on our shared cluster and pay
only for the inference time.

View pricing

Enterprise


LOOKING TO RUN AI ON YOUR OWN INFRASTRUCTURE?

Our enterprise solution offers maximum privacy and scale. Run AI models as an
API within your own cloud or infrastructure of choice.

Learn about our Enterprise solution


RESOURCES

 * Github
 * Documentation
 * Blog
 * Join our Discord

COMPANY

 * About
 * Contact us

 * 
 * 
 * 



Copyright © 2023 Mystic AI, Inc. All rights reserved.

 * Terms of Service
 * Privacy Policy