⚡️ FlashAttention-4: up to 1.3× faster than cuDNN on NVIDIA Blackwell →

Introducing Together AI's new look →

🔎 ATLAS: runtime-learning accelerators delivering up to 4x faster LLM inference →

⚡ Together GPU Clusters: self-service NVIDIA GPUs, now generally available →

📦 Batch Inference API: Process billions of tokens at 50% lower cost for most models →

🪛 Fine-Tuning Platform Upgrades: Larger Models, Longer Contexts →

Cookbooks

Build powerful AI apps by following our guides

Explore our collection of open-source example and demo apps by the Together AI team.

Showing 200+ models

RAG

Open Contextual RAG

An implementation of Contextual Retrieval using open models.

RAG

MultiModal RAG with Nvidia Deck

Multimodal RAG using Nvidia investor slides

Fine-Tuning

Conversation Finetuning

Fine-tuning LLMs on multi-step conversations.

Fine-Tuning

Summarization Long Context Finetuning

Long context fine-tuning to improve summarization capabilities.

Fine-Tuning

Long Context Finetuning For Repetition

Fine-tuning LLMs to repeat back words in long sequences.

Fine-Tuning

LoRA Inference and Fine-tuning

Perform LoRA fine-tuning and inference on Together AI.

Agents

Looping Agent Workflow

Build an agent that iteratively improves responses

Agents

Orchestrator Subtask Agent Workflow

Break down tasks into parallel subtasks to be executed by LLMs.

Agents

Parallel Agent Workflow

Run multiple LLMs in parallel and aggregate their solutions.

No search result

Try expanding your search or changing the filters.