Added Oct 28, 2026
Together AI
PaidCloud for running, fine-tuning and training open-source models
What is Together AI?
Together AI is a cloud platform for serverless inference, fine-tuning and GPU clusters built around open-source models such as Llama, Qwen, DeepSeek and Kimi. It is used by startups and labs that want fast, cheap access to open models at scale.
The serverless API offers many open models with OpenAI-compatible endpoints, and dedicated endpoints give reserved capacity. Fine-tuning supports LoRA and full training, and GPU clusters are available for training runs.
Together also publishes inference research and kernels used across the industry. Billing is per token for serverless use and per hour for dedicated hardware.
Features
- Serverless open-model API
- Dedicated endpoints
- Fine-tuning
- GPU clusters
- Batch inference
Tags
Releases
+ Submit new release- Listed
Together AI was added to the directory.
Organization
Together AI
πΊπΈ United States
Listed by kitio.ai Β· unverified owner
Pricing
- Pricing model
- Paid
- Paid options from
- Not listed
Together AI plans
Serverless Inference
Per 1M tokens
- Chat, vision, image, audio, video
- Cached input discounts
GPU Compute
$5.49 / hr (H100)
- H100, H200, B200, B300, GB200
- Pay as you go or reserved
Enterprise
Contact sales
- Dedicated inference
- Provisioned throughput
Prices in USD, checked Oct 28, 2026. Plans change often, so confirm on the Together AI site.Official pricing
Sponsored
Your AI tool here
A Featured launch puts your tool in this spot and on the home page for a week.
Top Together AI alternatives
View allModels & APIs
On-demand GPU pods and serverless endpoints for AI workloads
Models & APIs
Fast inference and fine-tuning platform for open models
Models & APIs
The main hub for open models, datasets and AI demo apps
Models & APIs
Run and deploy open-source AI models through a simple API
Compare Together AI
If you liked Together AI
Production inference and fine-tuning for open models on Nebius cloud
PaidModels & APIsMade in NetherlandsGPU cloud for AI training and inference with managed MLOps
PaidModels & APIsMade in NetherlandsLow-cost serverless API for hundreds of open-source models
PaidModels & APIsMade in United StatesOpen-source library for faster, low-memory LLM fine-tuning
FreemiumModels & APIsMade in United StatesAffordable model APIs and GPU cloud for open-source AI
PaidModels & APIsMade in United States
Pros and cons
Pros
- Wide open-model catalog
- Competitive token prices
- Fine-tuning and training in one place
Cons
- Requires prepaid credits
- Some models have limited capacity
- Dashboard is basic
Prompts & results
No prompts yet. Add your own prompt and output to help others use this tool.
Share a prompt
Reviews
Q&A
What is Together AI?
Together AI is a cloud platform for serverless inference, fine-tuning and GPU clusters built around open-source models such as Llama, Qwen, DeepSeek and Kimi. It is used by startups and labs that want fast, cheap access to open models at scale.
How much does Together AI cost?
Together AI is paid.
Is there a free version of Together AI?
No. Together AI is a paid tool.
What are the main features of Together AI?
Serverless open-model API, Dedicated endpoints, Fine-tuning, GPU clusters, Batch inference.
Who makes Together AI?
Together AI is made by Together AI.
What are the best alternatives to Together AI?
Popular alternatives include RunPod, Fireworks AI, Hugging Face.