Together AI logoModel provider · Bring your own key

Together AI in a visual AI workflow

Run Together AI's image and video models in a visual AI workflow — FLUX, Seedream, Kling, Veo and more, BYOK at Together's list price.

ImageVideoLLMstogether.ai
56
Models
21
Image
29
Video
3
Audio
3
Text

Together AI runs a broad inference platform; NodeTool integrates its image and video generation models — FLUX, Seedream, and popular video models — as nodes on the canvas. (Together also serves open LLMs; those are reachable in chat via the Together provider id.)

Drop a Together model into a graph, chain it with models from other providers, and share the whole pipeline as one file. Because each model is a node, putting two through the same prompt is a wiring change, not a rewrite.

Together is BYOK in NodeTool: set `TOGETHER_API_KEY` and calls go to Together at their price. The model list below is generated from Together's node manifest.

Set your key in NodeTool
TOGETHER_API_KEY

Calls go straight to Together AI with your key at their list price — NodeTool never proxies or marks up the request.

What you can build with Together AI

text to videoimage to videotext to imageimage to imageautomatic speech recognitiontext to speech

Supported Together AI models

Each model below is its own node in NodeTool — the id is what Together AI serves it under. This list is generated from Together AI's node manifest, so it tracks what the provider actually ships.

Image models

21 total
Seedream 3.0 — Text to Image
ByteDance-Seed/Seedream-3.0

Seedream 3.0 — text to image via Together AI serverless.

Seedream 4.0 — Text to Image
ByteDance-Seed/Seedream-4.0

Seedream 4.0 — text to image via Together AI serverless.

FLUX.1 Kontext Max — Text to Image
black-forest-labs/FLUX.1-kontext-max

FLUX.1 Kontext Max — text to image via Together AI serverless.

FLUX.1 Kontext Max — Image to Image
black-forest-labs/FLUX.1-kontext-max

FLUX.1 Kontext Max — image to image via Together AI serverless.

FLUX.1 Kontext Pro — Text to Image
black-forest-labs/FLUX.1-kontext-pro

FLUX.1 Kontext Pro — text to image via Together AI serverless.

FLUX.1 Kontext Pro — Image to Image
black-forest-labs/FLUX.1-kontext-pro

FLUX.1 Kontext Pro — image to image via Together AI serverless.

FLUX.1 Schnell — Text to Image
black-forest-labs/FLUX.1-schnell

FLUX.1 Schnell — text to image via Together AI serverless.

FLUX.1.1 Pro — Text to Image
black-forest-labs/FLUX.1.1-pro

FLUX.1.1 Pro — text to image via Together AI serverless.

FLUX.2 Dev — Text to Image
black-forest-labs/FLUX.2-dev

FLUX.2 Dev — text to image via Together AI serverless.

FLUX.2 Dev — Image to Image
black-forest-labs/FLUX.2-dev

FLUX.2 Dev — image to image via Together AI serverless.

FLUX.2 Flex — Text to Image
black-forest-labs/FLUX.2-flex

FLUX.2 Flex — text to image via Together AI serverless.

FLUX.2 Flex — Image to Image
black-forest-labs/FLUX.2-flex

FLUX.2 Flex — image to image via Together AI serverless.

FLUX.2 Pro — Text to Image
black-forest-labs/FLUX.2-pro

FLUX.2 Pro — text to image via Together AI serverless.

FLUX.2 Pro — Image to Image
black-forest-labs/FLUX.2-pro

FLUX.2 Pro — image to image via Together AI serverless.

Flash Image 2.5 — Text to Image
google/flash-image-2.5

Flash Image 2.5 — text to image via Together AI serverless.

Gemini 3 Pro Image — Text to Image
google/gemini-3-pro-image

Gemini 3 Pro Image — text to image via Together AI serverless.

Gemini 3 Pro Image — Image to Image
google/gemini-3-pro-image

Gemini 3 Pro Image — image to image via Together AI serverless.

Imagen 4.0 Fast — Text to Image
google/imagen-4.0-fast

Imagen 4.0 Fast — text to image via Together AI serverless.

Imagen 4.0 Preview — Text to Image
google/imagen-4.0-preview

Imagen 4.0 Preview — text to image via Together AI serverless.

Ideogram 3.0 — Text to Image
ideogram/ideogram-3.0

Ideogram 3.0 — text to image via Together AI serverless.

Stable Diffusion 3 Medium — Text to Image
stabilityai/stable-diffusion-3-medium

Stable Diffusion 3 Medium — text to image via Together AI serverless.

Video models

29 total
Seedance 1.0 Lite — Text to Video
ByteDance/Seedance-1.0-lite

Seedance 1.0 Lite — text to video via Together AI serverless.

Seedance 1.0 Lite — Image to Video
ByteDance/Seedance-1.0-lite

Seedance 1.0 Lite — image to video via Together AI serverless.

Seedance 1.0 Pro — Text to Video
ByteDance/Seedance-1.0-pro

Seedance 1.0 Pro — text to video via Together AI serverless.

Seedance 1.0 Pro — Image to Video
ByteDance/Seedance-1.0-pro

Seedance 1.0 Pro — image to video via Together AI serverless.

Veo 2.0 — Text to Video
google/veo-2.0

Veo 2.0 — text to video via Together AI serverless.

Veo 2.0 — Image to Video
google/veo-2.0

Veo 2.0 — image to video via Together AI serverless.

Veo 3.0 — Text to Video
google/veo-3.0

Veo 3.0 — text to video via Together AI serverless.

Veo 3.0 — Image to Video
google/veo-3.0

Veo 3.0 — image to video via Together AI serverless.

Veo 3.0 + Audio — Text to Video
google/veo-3.0-audio

Veo 3.0 + Audio — text to video via Together AI serverless.

Kling 2.1 Master — Text to Video
kwaivgI/kling-2.1-master

Kling 2.1 Master — text to video via Together AI serverless.

Kling 2.1 Master — Image to Video
kwaivgI/kling-2.1-master

Kling 2.1 Master — image to video via Together AI serverless.

Kling 2.1 Pro — Text to Video
kwaivgI/kling-2.1-pro

Kling 2.1 Pro — text to video via Together AI serverless.

Kling 2.1 Pro — Image to Video
kwaivgI/kling-2.1-pro

Kling 2.1 Pro — image to video via Together AI serverless.

Kling 2.1 Standard — Text to Video
kwaivgI/kling-2.1-standard

Kling 2.1 Standard — text to video via Together AI serverless.

Kling 2.1 Standard — Image to Video
kwaivgI/kling-2.1-standard

Kling 2.1 Standard — image to video via Together AI serverless.

Mini Max Hailuo 02 — Text to Video
minimax/hailuo-02

MiniMax Hailuo 02 — text to video via Together AI serverless.

Mini Max Hailuo 02 — Image to Video
minimax/hailuo-02

MiniMax Hailuo 02 — image to video via Together AI serverless.

Mini Max Video 01 Director — Text to Video
minimax/video-01-director

MiniMax Video 01 Director — text to video via Together AI serverless.

Mini Max Video 01 Director — Image to Video
minimax/video-01-director

MiniMax Video 01 Director — image to video via Together AI serverless.

Sora 2 — Text to Video
openai/sora-2

Sora 2 — text to video via Together AI serverless.

Sora 2 — Image to Video
openai/sora-2

Sora 2 — image to video via Together AI serverless.

Sora 2 Pro — Text to Video
openai/sora-2-pro

Sora 2 Pro — text to video via Together AI serverless.

Sora 2 Pro — Image to Video
openai/sora-2-pro

Sora 2 Pro — image to video via Together AI serverless.

Pix Verse v5 — Text to Video
pixverse/pixverse-v5

PixVerse v5 — text to video via Together AI serverless.

Pix Verse v5 — Image to Video
pixverse/pixverse-v5

PixVerse v5 — image to video via Together AI serverless.

Vidu 2.0 — Text to Video
vidu/vidu-2.0

Vidu 2.0 — text to video via Together AI serverless.

Vidu 2.0 — Image to Video
vidu/vidu-2.0

Vidu 2.0 — image to video via Together AI serverless.

Vidu Q1 — Text to Video
vidu/vidu-q1

Vidu Q1 — text to video via Together AI serverless.

Vidu Q1 — Image to Video
vidu/vidu-q1

Vidu Q1 — image to video via Together AI serverless.

Audio models

3 total
Orpheus 3 B — Text to Speech
canopylabs/orpheus-3b-0.1-ft

Orpheus 3B — text to speech via Together AI serverless.

Cartesia Sonic — Text to Speech
cartesia/sonic

Cartesia Sonic — text to speech via Together AI serverless.

Kokoro 82 M — Text to Speech
hexgrad/Kokoro-82M

Kokoro 82M — text to speech via Together AI serverless.

Text models

3 total
Voxtral Mini 3 B — Transcribe
mistralai/Voxtral-Mini-3B-2507

Voxtral Mini 3B — transcribe via Together AI serverless.

Parakeet TDT 0.6 B v3 — Transcribe
nvidia/parakeet-tdt-0.6b-v3

Parakeet TDT 0.6B v3 — transcribe via Together AI serverless.

Whisper Large v3 — Transcribe
openai/whisper-large-v3

Whisper Large v3 — transcribe via Together AI serverless.

Frequently asked

How do I connect Together AI?
Add your key as `TOGETHER_API_KEY` in NodeTool. Together nodes call the API directly with your key.
Which Together AI models does NodeTool support?
The image and video generation models are nodes (catalog below); Together's open-weight LLMs are available in chat and agent nodes via the Together provider.
Is there a NodeTool fee on Together AI?
No — bring your own key and pay Together's list price. NodeTool adds nothing per call.

Other providers

Run Together AI your way.

Download NodeTool Studio and build across image, video, audio, and text with your own keys.