Contact Sales

Talk to an engineer

Work with FDEs who scale inference to trillions of tokens

Talk to an engineer

Our team of AI experts is ready to show you how Together AI can accelerate your generative AI lifecycle.

Open models run faster and cost less on Together AI. We’ll prove it on your workload.

Every FDE comes from the team on call for some of the largest inference deployments in the world, including Cursor's.

Open models run faster and cost less on Together AI. We’ll prove it on your workload.

Get a custom walkthrough of our platform

Reserved capacity with guaranteed throughput

Benchmark your workload

against your current provider before you commit

Reserved capacity with guaranteed throughput

Get started with your Enterprise trial

Volume pricing that scales with your usage

Post-train open models on your data

to match or beat your closed-model baseline

Volume pricing that scales with your usage

Find the ideal custom plan and pricing

Custom and fine-tuned models on dedicated endpoints

Explore how our products best fit your use case

Configs tuned to your workload for your latency and cost targets

Discuss a custom model or solution to fit your specific needs

A POC on your workload before you sign

Forward Deployed Engineering support

serving 400t+ tokens a month for

preferred partner
SOC 2 Type II
ISO 27001:2022

preferred partner
SOC 2 Type II
ISO 27001:2022

"We’ve been thoroughly impressed with the Together Enterprise Platform. It has delivered a 2x reduction in latency (time to first token) and cut our costs by approximately a third. These improvements allow us to launch AI-powered features and deliver lightning-fast experiences faster than ever before."

Caiming Xiong

VP, Salesforce AI Research

Decagon shape with black background and thin dark gray outline on a white backdrop.

6x lower cost per turn

"Together helped us push latency down by optimizing our models with techniques like speculative decoding, and they've been a reliable production partner."

Max Lu

Head of Research

485ms → 29ms TTFT

We researched several leading inference providers but ultimately chose to go with Together AI because price-performance was significantly better.

Mark McQuade

CEO

2x faster per step

Working with Together AI has allowed Yutori to scale without failures. That's important.

Dhruv Batra

Co-founder and Chief Scientist

2x lower latency

We've been thoroughly impressed with Together. They delivered a 2x reduction in latency and cut our costs by approximately a third.

Caiming Xiong

View All Stories

6x lower cost per turn

"Together helped us push latency down by optimizing our models with techniques like speculative decoding, and they've been a reliable production partner."

Max Lu

Head of Research

485ms → 29ms TTFT

We researched several leading inference providers but ultimately chose to go with Together AI because price-performance was significantly better.

Mark McQuade

CEO

2x faster per step

Working with Together AI has allowed Yutori to scale without failures. That's important.

Dhruv Batra

Co-founder and Chief Scientist

2x lower latency

We've been thoroughly impressed with Together. They delivered a 2x reduction in latency and cut our costs by approximately a third.

Caiming Xiong

View All Stories