⚡️ 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 Instant 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 →

Model library

Leading open models,
ready for production

Browse and compare a growing library of models available on Together AI

Abstract 3D geometric shapes consisting of intersecting blue, purple, and orange discs and planes on a white background.Abstract blue and purple gradient shapes on a light blue background.
All
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Showing 200+ models
Dropdown
Chat
NIM Mistral-NeMo 12B Instruct
  • Parameters
    12B
  • Deployment
    Dedicated Inference
No items found.
Chat

nim/nv-mistralai/mistral-nemo-12b-instruct

Meta

Chat
Cogito V1 Preview Llama 3B
  • Parameters
    3B
  • Deployment
    Dedicated Inference
No items found.
Chat
Code
Reasoning

deepcogito/cogito-v1-preview-llama-3B

Deep Cogito

Chat
DBRX-Instruct
  • Parameters
    132B
No items found.
LLM

DataBricks

Chat
NIM Mixtral 8x22B Instruct v0.1
  • Parameters
    141B
  • Deployment
    Dedicated Inference
No items found.
Chat

nim/mistralai/mixtral-8x22b-instruct-v01

Meta

Chat
Llama 3.1 8B
  • Parameters
    8B
  • Deployment
    Dedicated Inference
Function Calling
JSON Mode
LLM

meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo

Meta

Chat
Gemma 3 1B
  • Parameters
    1B
  • Deployment
    Dedicated Inference
No items found.
Chat
Code
Vision

google/gemma-3-1b-it

Google

Chat
Gemma 3 4B
  • Parameters
    4B
  • Deployment
    Dedicated Inference
No items found.
Chat
Code
Vision

google/gemma-3-4b-it

Google

Image
FLUX.1 [schnell]

  • Price/MP

    $0.0027
  • Parameters
    12B
No items found.
Image

black-forest-labs/FLUX.1-schnell

Black Forest Labs

Chat
Llama 3.2 3B Instruct Turbo
  • Parameters
    3B
  • Deployment
    Dedicated Inference
Function Calling
JSON Mode
LLM

meta-llama/Llama-3.2-3B-Instruct-Turbo

Meta

Chat
Gemma Instruct (2B)
  • Parameters
    2B
  • Deployment
    Dedicated Inference
No items found.
LLM

google/gemma-2b-it

Google

Chat
Qwen2.5 7B Instruct Turbo

  • Input/1M

    $0.30

  • Output/1M

    $0.30
  • Parameters
    7B
Function Calling
JSON Mode
LLM

Qwen/Qwen2.5-7B-Instruct-Turbo

Qwen

Chat
Mistral
  • Parameters
    7B
No items found.
LLM

Mistral AI

Chat
Mixtral 8x7B Instruct v0.1

  • Input/1M

    $0.60

  • Output/1M

    $0.60
  • Parameters
    46.7B
No items found.
LLM

mistralai/Mixtral-8x7B-Instruct-v0.1

Mistral AI

Chat
Mixtral 8x7B v0.1
  • Parameters
    46B
No items found.
LLM

Mistral AI

New
Chat
Qwen3 32B
  • Parameters
    32B
  • Deployment
    Dedicated Inference
No items found.
Chat

Qwen/Qwen3-32B

Qwen

Chat
Mistral (7B) Instruct v0.2

  • Input/1M

    $0.20

  • Output/1M

    $0.20
  • Parameters
    7.2B
JSON Mode
LLM

mistralai/Mistral-7B-Instruct-v0.2

Mistral AI

Moderation
Llama Guard (7B)
  • Parameters
    7B
No items found.
Moderation

Meta

Chat
MythoMax-L2
  • Parameters
    13B
No items found.
LLM

Gryphe

Embeddings
M2-BERT 80M 2K Retrieval
  • Parameters
    80M
No items found.
Embeddings

Together AI

Embeddings
M2-BERT 80M 8K Retrieval
  • Parameters
    80M
No items found.
Embeddings

Together AI

New
Chat
Qwen3 0.6B
  • Parameters
    751.6M
  • Deployment
    Dedicated Inference
No items found.
Chat

Qwen/Qwen3-0.6B

Qwen

New
Chat
Qwen3 0.6B Base
  • Parameters
    0.6B
  • Deployment
    Dedicated Inference
No items found.
LLM

Qwen/Qwen3-0.6B-Base

Qwen

New
Chat
Qwen3 1.7B
  • Parameters
    1.7B
  • Deployment
    Dedicated Inference
No items found.
Chat

Qwen/Qwen3-1.7B

Qwen

New
Chat
Qwen3 1.7B Base
  • Parameters
    1.7B
  • Deployment
    Dedicated Inference
No items found.
LLM

Qwen/Qwen3-1.7B-Base

Qwen

New
Chat
Qwen3 14B Base
  • Parameters
    14.8B
  • Deployment
    Dedicated Inference
No items found.
LLM

Qwen/Qwen3-14B-Base

Qwen

No search result

Try expanding your search or changing the filters.

Deployment options

Run models using different deployment options depending on latency needs, traffic patterns, and infrastructure control.

  • Serverless

  • Inference

Serverless Inference

Real-time

A fully managed inference API that automatically scales with request volume.

Best for

Variable or unpredictable traffic

Rapid prototyping and iteration

Cost-sensitive or early-stage production workloads

Get started
Explore Docs

Batch

Process massive workloads of up to 30 billion tokens asynchronously, at up to 50% less cost.

Best for

Classifying large datasets

Offline summarization

Synthetic data generation

Get started
Explore Docs

Dedicated Inference

Dedicated Model Inference

An inference endpoint backed by reserved, isolated compute resources and the Together AI inference engine.

Best for

Predictable or steady traffic

Latency-sensitive applications

High-throughput production workloads

Get started
Explore Docs

Dedicated Container Inference

Run inference with your own engine and model on fully-managed, scalable infrastructure.

Best for

Generative media models

Non-standard runtimes

Custom inference pipelines

Contact sales
Explore Docs

Explore model providers

Leading model providers rely on Together AI infrastructure to deploy, 
scale, and run their models in production.

5 models

Anthropic

5 models

xAI

5 models

Deepgram

5 models

Meta

5 models

Qwen

5 models

Black Forest Labs

5 models

Google

5 models

Mistral AI

5 models

Arcee AI

5 models

Deep Cogito

5 models

DeepSeek

5 models

Minimax AI

5 models

OpenAI

5 models

Kuaishou

5 models

ByteDance

5 models

SCB10X

5 models

Moonshot AI

5 models

Rime

5 models

ZAI

5 models

Alibaba

5 models

HiDream.ai

5 models

NVIDIA

5 models

Stability AI

5 models

Together AI

5 models

BAAI

5 models

BERT

5 models

Cartesia

5 models

Gryphe

5 models

LG AI Research

5 models

Refuel

5 models

RunDiffusion

5 models

ServiceNow AI

5 models

Vidu

5 models

Agentica & Together AI

5 models

Alibaba-NLP

5 models

Canopy Labs

5 models

DataBricks

5 models

Essential AI

5 models

Ideogram

5 models

Liquid AI

5 models

Lykon

5 models

Marin Community

5 models

Microsoft

5 models

Mixedbread AI

5 models

Nous Research

5 models

Perplexity AI

5 models

PixVerse

5 models

Salesforce

5 models

Upstage AI

5 models

Virtue AI

5 models

WhereIsAI

5 models

hexgrad

5 models

intfloat