Our products
RESOURCES
Our products
RESOURCES
Plans for all sizes
Pricing plans
Pricing plans
We believe MAKO should be accessible to all companies, no matter the size.
Free
$0/month
5 free generations every 30 days
Support for 2 backends
Discord support
Up to 5 attempts per request
5 free tunes every 30 days
Free
$0/month
5 free generations every 30 days
Support for 2 backends
Discord support
Up to 5 attempts per request
5 free tunes every 30 days
Free
$0/month
5 free generations every 30 days
Support for 2 backends
Discord support
Up to 5 attempts per request
5 free tunes every 30 days
Free
$0/month
5 free generations every 30 days
Support for 2 backends
Discord support
Up to 5 attempts per request
5 free tunes every 30 days

Optimize
$10,000/month
Generate
Coming soon
Pro
Most popular
Unlimited generations
Up to 10 seats (Generate) / up to 10 seats (Optimize)
Support for 2 languages & 2 hardware targets
Engineering support via private Slack
Unlimited tunes for up to 100+ pretrained models
Latest vLLM & SGLang support

Optimize
$10,000/month
Generate
Coming soon
Pro
Most popular
Unlimited generations
Up to 10 seats (Generate) / up to 10 seats (Optimize)
Support for 2 languages & 2 hardware targets
Engineering support via private Slack
Unlimited tunes for up to 100+ pretrained models
Latest vLLM & SGLang support

Optimize
$10,000/month
Generate
Coming soon
Pro
Most popular
Unlimited generations
Up to 10 seats (Generate) / up to 10 seats (Optimize)
Support for 2 languages & 2 hardware targets
Engineering support via private Slack
Unlimited tunes for up to 100+ pretrained models
Latest vLLM & SGLang support

Optimize
$10,000/month
Generate
Coming soon
Pro
Most popular
Unlimited generations
Up to 10 seats (Generate) / up to 10 seats (Optimize)
Support for 2 languages & 2 hardware targets
Engineering support via private Slack
Unlimited tunes for up to 100+ pretrained models
Latest vLLM & SGLang support
Optimize
Contact sales
Generate
Contact sales
Enterprise
Everything in Pro
Deploy agent on-prem
All backends & hardware targets supported
8h incident response SLA
Priority Engineering Support
Priority Feature Requests
Optimize
Contact sales
Generate
Contact sales
Enterprise
Everything in Pro
Deploy agent on-prem
All backends & hardware targets supported
8h incident response SLA
Priority Engineering Support
Priority Feature Requests
Optimize
Contact sales
Generate
Contact sales
Enterprise
Everything in Pro
Deploy agent on-prem
All backends & hardware targets supported
8h incident response SLA
Priority Engineering Support
Priority Feature Requests
Optimize
Contact sales
Generate
Contact sales
Enterprise
Everything in Pro
Deploy agent on-prem
All backends & hardware targets supported
8h incident response SLA
Priority Engineering Support
Priority Feature Requests
Features
Free
Pro
Enterprise

MakoGenerate
Generations (5 free / Unlimited)
Backends supported
Attempts per request
Community support
Deployment
Priority support
5 free every 30 days
Up to 2
Up to 5
Discord
Unlimited
Up to 2 langs & 2 HW targets
Unlimited
Private Slack support
Unlimited
All backends & hardware targets
Unlimited
8-hour incident response SLA
Deploy agent on-prem
Priority support
MakoOptimize
Tunes per 30 days
vLLM / SGLang support
Seats
Community support
Deployment
Priority support
5 free
Latest vLLM only
Discord
On your own infra (limited)
Unlimited (100+ models)
Latest vLLM + SGLang
Up to 10
Private Slack support
On your own infra
Unlimited
Deploy agent on-prem
Unlimited
8-hour incident response SLA
Deploy on-prem
Priority support
Features
Free
MakoGenerate
Generations (5 free / Unlimited)
Backends supported
Attempts per request
Community support
Deployment
Priority support
5 free every 30 days
Up to 2
Up to 5
Discord
MakoOptimize
Tunes per 30 days
vLLM / SGLang support
Seats
Community support
Deployment
Priority support
5 free
Latest vLLM only
Discord
On your own infra (limited)
Features
Free
MakoGenerate
Generations (5 free / Unlimited)
Backends supported
Attempts per request
Community support
Deployment
Priority support
5 free every 30 days
Up to 2
Up to 5
Discord
MakoOptimize
Tunes per 30 days
vLLM / SGLang support
Seats
Community support
Deployment
Priority support
5 free
Latest vLLM only
Discord
On your own infra (limited)
Features
Free
Pro
Enterprise

MakoGenerate
Generations (5 free / Unlimited)
Backends supported
Attempts per request
Community support
Deployment
Priority support
5 free every 30 days
Up to 2
Up to 5
Discord
Unlimited
Up to 2 langs & 2 HW targets
Unlimited
Private Slack support
Unlimited
All backends & hardware targets
Unlimited
8-hour incident response SLA
Deploy agent on-prem
Priority support
MakoOptimize
Tunes per 30 days
vLLM / SGLang support
Seats
Community support
Deployment
Priority support
5 free
Latest vLLM only
Discord
On your own infra (limited)
Unlimited (100+ models)
Latest vLLM + SGLang
Up to 10
Private Slack support
On your own infra
Unlimited
Deploy agent on-prem
Unlimited
8-hour incident response SLA
Deploy on-prem
Priority support
What kinds of applications benefit from Mako?
Large language models, transformer architectures, and high-throughput inference workloads see significant performance gains. Computer vision models, recommendation systems, and any GPU-bottlenecked application also benefit from automated kernel optimization.
Do I need to know CUDA to use Mako?
Not at all. MakoOptimize handles all GPU programming complexity automatically. You can describe logic in Python-like syntax or natural language, and Mako handles the rest.
Can Mako be used in production today?
Yes. We're working with early adopters in production environments now. Join the waitlist to get early access and hands-on support.
What kinds of applications benefit from Mako?
Large language models, transformer architectures, and high-throughput inference workloads see significant performance gains. Computer vision models, recommendation systems, and any GPU-bottlenecked application also benefit from automated kernel optimization.
Do I need to know CUDA to use Mako?
Not at all. MakoOptimize handles all GPU programming complexity automatically. You can describe logic in Python-like syntax or natural language, and Mako handles the rest.
Can Mako be used in production today?
Yes. We're working with early adopters in production environments now. Join the waitlist to get early access and hands-on support.
What kinds of applications benefit from Mako?
Large language models, transformer architectures, and high-throughput inference workloads see significant performance gains. Computer vision models, recommendation systems, and any GPU-bottlenecked application also benefit from automated kernel optimization.
Do I need to know CUDA to use Mako?
Not at all. MakoOptimize handles all GPU programming complexity automatically. You can describe logic in Python-like syntax or natural language, and Mako handles the rest.
Can Mako be used in production today?
Yes. We're working with early adopters in production environments now. Join the waitlist to get early access and hands-on support.
What kinds of applications benefit from Mako?
Large language models, transformer architectures, and high-throughput inference workloads see significant performance gains. Computer vision models, recommendation systems, and any GPU-bottlenecked application also benefit from automated kernel optimization.
Do I need to know CUDA to use Mako?
Not at all. MakoOptimize handles all GPU programming complexity automatically. You can describe logic in Python-like syntax or natural language, and Mako handles the rest.
Can Mako be used in production today?
Yes. We're working with early adopters in production environments now. Join the waitlist to get early access and hands-on support.
Products
company
Copyright © 2025 Mako. All rights reserved.
Products
company
Copyright © 2025 Mako. All rights reserved.
Products
company
Copyright © 2025 Mako. All rights reserved.
Products
company
Copyright © 2025 Mako. All rights reserved.