In the fast-paced world of AI, efficiency and cost-effectiveness are key. Together AI, a company known for its relentless pursuit of optimization, has just announced a groundbreaking update that's sure to make waves in the industry. Hold on to your hats, because we're diving into a 5x price reduction on Together API, thanks to faster inference! ๐ŸŽ‰

Innovations and Optimizations ๐Ÿง ๐Ÿ’ผ

Together AI is no stranger to innovation. Their research team has been at the forefront of today's fastest optimizations, developing techniques like FlexGen and algorithms like FlashAttention-2. Since launching Together API, their cloud platform for running leading open-source AI models, they've been hard at work optimizing their inference stack. And guess what? They're not stopping anytime soon, with more speed-ups on the horizon.

More Speed, More Savings ๐ŸŽ๏ธ๐Ÿ’ธ

With faster performance, Together AI can process more transactions per GPU, leading to better cost efficiency. It's like upgrading from a bicycle to a race car without burning extra fuel! Today's announcement brings updated pricing that offers more for less. Let's break down the numbers:

Inference Pricing for Chat, Language, and Code Models

Model Size
Price per 1K tokens
Up to 3B
$0.0001
3.1B - 7B
$0.0002
7.1B - 20B
$0.0004
20.1B - 40B
$0.001
40.1B - 70B
$0.003

Pricing for Fine-Tuned Models

Model Size
Price per 1K tokens
Price per hour hosting
Up to 3B
$0.0001
$0.52
3.1B - 7B
$0.0002
$0.52
7.1B - 20B
$0.0004
Coming soon
20.1B - 40B
$0.001
Coming soon
40.1B - 70B
$0.003
Coming soon

Image Models Pricing

Image Size
25 steps
50 steps
75 steps
100 steps
Up to 300 kilopixels (512 x 512)
$0.001
$0.002
$0.0035
$0.005
Up to 1.1 megapixels (1024 x 1024)
$0.01
$0.02
$0.035
$0.05

Get Started Today! ๐ŸŽ

Ready to jump in? Head to api.together.ai and start running more efficient inference with their Playgrounds and APIs. New users even get $25 in free credits to kickstart their journey.

My Thoughts: A New Era of AI ๐ŸŒŸ

Together AI's announcement is more than just a price reduction; it's a testament to the power of innovation and optimization. By focusing on efficiency and delivering value, they've set a new standard for the industry.
The detailed pricing structure, tailored to different model sizes and types, reflects a thoughtful approach to meeting diverse needs. It's like having a personalized menu for every AI enthusiast, from hobbyists to professionals.
In a world where every penny counts, Together AI's commitment to providing more for less is a refreshing and welcome change. It's not just about cutting costs; it's about empowering more people to explore, create, and innovate with AI.
So here's to faster inference, reduced prices, and a future where AI is accessible to all. Together, we're building a brighter tomorrow! ๐ŸŒˆ๐Ÿ› ๏ธ

What are your thoughts on Together AI's pricing update? Share your insights and join the conversation below! ๐Ÿ—จ๏ธ๐Ÿ’ฌ
Relate Posts
LLM Open Challenges 3: Do we always need GPUs? (3 min)
Lazy loaded image
LLM Open Challenges 1: How to improve efficiencies of chat interface? (3min read)
Lazy loaded image
๐ŸŒ LLM Open Challenges 2: Large Language Models for Non-English Languages: Challenges and Perspectives ๐Ÿš€ย (3min read)
Lazy loaded image
RAVEN: Unleashing the Power of In-Context Learning ๐Ÿš€ย (3min read)
Lazy loaded image
Introducing DoctorGPT: Your Private AI Doctor ๐Ÿฉบ๐Ÿ’ปย (3min read)
Lazy loaded image
Exploring Open-Source AGI Projects: Use Cases and Comparisons (5min read)
Lazy loaded image
The Pioneering Spirit of AI: A Journey Toward Human-Level Intelligence ๐Ÿš€ย (5min read)๐Ÿค–๐Ÿ’กTrusting the Machines: A Comprehensive Guide to Evaluating Large Language Models' Alignment (5min read)
Loading...
raygorous๐Ÿ‘ป
raygorous๐Ÿ‘ป
a man with a bit of everything๐Ÿ”ฅ
Latest posts
Top 5 Most Surprisings From Claude Code Source Map
Mar 31, 2026
๐Ÿง  Why We Feel Empty in a World That Gives Us Everything
Mar 22, 2026
Zen Is Not Calm. Zen Is a Weapon.
Jan 19, 2026
Claude Code: A Highly Agentic Coding Assistant โ€” A Deep, Practical Review ๐Ÿ’ป
Jan 19, 2026
Elon Muskโ€™s 15 Daily Prompts That Rewired How I Think About Hard Problems
Nov 30, 2025
ๆž็ซฏไผ˜็ง€ vs ไธ€่ˆฌไผ˜็ง€
Nov 29, 2025
Announcement
Doing some summarization of the current LLM&GenAI works since August. Stay tuned ๐ŸŽผ
ย