Flora and Hedra: a canvas for ideas, and the infrastructure underneath
Flora chains third-party models on a visual canvas. Hedra operates the GPU clusters and inference engine models like those run on, and post-trains them for customers.
export HEDRA_API_KEY="<key_id>:<secret>"
curl -X POST \
"https://api.hedra.com/v3/models/flux-dev" \
-H "Authorization: Key $HEDRA_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "input": {
"prompt": "A moodboard frame: brushed steel kettle on a walnut counter, overcast light",
"aspect_ratio": "4:3"
} }'A more modern way to work
Skip the model aggregators. Hedra Agent and Workspaces give your team an autonomous agent that supercharges your workflows with a superintelligent understanding of the latest models: brief it in a shared space and it plans, generates, and edits across video, image, speech, and music, with your team and your agents working alongside it.
GPU infrastructure, an inference engine, and post-training research
Hedra operates GPU clusters and the inference engine that runs diffusion and autoregressive media models on them 8x faster. The same research team post-trains models for customers: supervised fine-tuning, LoRA training, and GRPO, on your data.
Hedra and Flora: focus at a glance
Flora is a workspace that orchestrates other makers' models. Hedra serves and post-trains models on infrastructure it operates.
| Dimension | Hedra | Flora AI |
|---|---|---|
| What it is | GPU infrastructure, inference and post-training research | A visual canvas for exploring ideas with AI models |
| Core technology | Hedra's inference engine, its own GPU clusters, and post-training (SFT, LoRA, GRPO) | A node-based canvas that chains third-party image, video and text models |
| Models | Open-weight models on Hedra's engine, models post-trained for you, and partner models through a gateway | Other providers' models, called from the canvas |
| How you connect | API, SDK, CLI, MCP, and Hedra Workspaces | Flora canvas in the browser |
| Where inference runs | Hedra's GPU clusters, or your own | Flora's cloud, calling model providers |
| Best fit | Teams building visual products who need inference, capacity and custom models | Designers exploring ideas visually on a canvas |
The models a canvas would chain, on Hedra infrastructure
Image rates are per generation; video rates are per second of generated clip. Open weights run on Hedra's engine; partner models come through the gateway.
| Provider | Model ID | Rate |
|---|---|---|
| Black Forest Labs | flux-dev | 2.86¢/MP · open weights |
| Black Forest Labs | flux2-pro | 3¢/image · text to image |
| nano-banana-pro | 15¢/image · 1K | |
| OpenAI | gpt-image-2 | 14.29¢/image · 1K medium |
| Kling | kling-v3 | 16.8¢/s · 1080p |
| Alibaba | wan-3-0 | 20¢/s · 1080p |
FAQs
- How do Hedra and Flora fit together?
- Flora is a canvas for arranging model calls visually, on top of other companies' inference. Hedra is that inference: GPU clusters, the engine that runs the models, and post-training for customers. Hedra Workspaces is a shared canvas too, for teams and their agents, built on the same engine.
- What does Hedra actually operate?
- GPU clusters, the inference engine that serves media models on them, and a research team that pre-trains and post-trains models. Open-weight models and models post-trained for customers run on that engine, on Hedra's clusters or inside your perimeter. Partner models that only their makers serve are reached through Hedra's gateway so one request shape covers both.
- Can this run on our own hardware?
- Yes. Hedra Inference deploys on your Kubernetes or bare metal, including air-gapped environments, across NVIDIA, AMD, AWS Trainium, Google TPU, and custom accelerators. Weights, data, and the control plane stay on infrastructure you operate.
