Together AI | The AI Native Cloud

Reliably build, deploy, and scale AI native apps — benefit from cutting-edge research, complete developer experience, and unmatched price-performance.

收录于 9 个月前更新于 9 个月前正常收录

详细内容

Build on the AI Native Cloud

Engineered for AI natives, powered by cutting-edge research

Start building now Contact sales

The Together AI Platform

Accelerate training, fine-tuning and inference on performance-optimized GPU clusters

Reliable at production scale

Built for scale, with customers going to trillions of tokens in a matter of hours without any depletion in experience.

Industry-leading unit economics

Continuously optimizing across inference and training to keep improving performance, delivering better total cost of ownership.

Frontier AI systems research

Proven infra and research teams ensure the latest models, hardware, and techniques are made available on day 1.

Full stack development for AI ‑ native apps

Model Library Inference Fine-Tuning Pre-Training GPU Clusters

Model Library

Evaluate and build with open-source and specialized models for chat, images, videos, code, and more.

Migrate from closed models with OpenAI-compatible APIs.

Start building now

together.ai

Chat\
\
\
\
Kimi K2 Thinking →\
\
New

Chat\
\
\
\
Qwen3 235B A22B Instruct 2507 FP8 →

Chat\
\
\
\
gpt-oss-120B →\
\
New

Chat\
\
\
\
DeepSeek-V3.1 →\
\
New

Chat\
\
\
\
Apriel-1.5-15b-Thinker →\
\
Free

Image\
\
\
\
Gemini Flash Image 2.5 (Nano Banana) →\
\
New

Video\
\
\
\
Sora 2 Pro →\
\
New

Chat\
\
\
\
GLM-4.6 →\
\
New

Inference

Reliably deploy models with unmatched price-performance at scale. Benefit from inference-focused innovations like the ATLAS speculator system and Together Inference Engine.

Deploy on hardware of choice, such as NVIDIA GB200 NVL72 and GB300 NVL72.

Learn more

Fine-Tuning

Fine-tune open-source models with your data to create task-specific, fast, and cost-effective models that are 100% yours.

Easily deploy into production through Together AI's highly performant inference stack.

Learn more

Pre-Training

Securely and cost effectively train your own models from the ground up, leveraging research breakthroughs such as Together Kernel Collection (TKC) for reliable and fast training.