Higgsfield and Hedra: a gateway with presets, and the infrastructure underneath
Higgsfield wraps partner video models in camera presets and credit bundles, beside its Soul image model. Hedra operates the GPU clusters and inference engine, and post-trains models for customers.
export HEDRA_API_KEY="<key_id>:<secret>"
curl -X POST \
"https://api.hedra.com/v3/models/kling-26-pro" \
-H "Authorization: Key $HEDRA_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "input": {
"prompt": "Low-angle tracking shot along a lava flow at dusk",
"aspect_ratio": "16:9",
"resolution": "1080p",
"duration_ms": 5000
} }'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 Higgsfield: focus at a glance
Higgsfield is a gateway and creative product with presets and credit bundles. Hedra runs the infrastructure under products like it and post-trains models on it.
| Dimension | Hedra | Higgsfield |
|---|---|---|
| What it is | GPU infrastructure, inference and post-training research | Cinematic short clips for social |
| Core technology | Hedra's inference engine, its own GPU clusters, and post-training (SFT, LoRA, GRPO) | Camera-control presets over partner video models, plus its Soul image model |
| Models | Open-weight models on Hedra's engine, models post-trained for you, and partner models through a gateway | Its own Soul model and third-party video models it resells |
| How you connect | API, SDK, CLI, MCP, and Hedra Workspaces | Higgsfield app and API |
| Where inference runs | Hedra's GPU clusters, or your own | Higgsfield's cloud and its providers' clouds |
| Best fit | Teams building visual products who need inference, capacity and custom models | Social creators making short cinematic clips |
Video models on Hedra infrastructure, priced per second
Rates per second of generated video at the resolution shown. Open-weight models run on Hedra's engine; partner models are reached through the gateway.
| Provider | Model ID | Rate |
|---|---|---|
| Kling | kling-v3 | 16.8¢/s · 1080p |
| veo-31 | 39.29¢/s · 1080p | |
| ByteDance | seedance-25 | 79.09¢/s · 1080p |
| Alibaba | wan-3-0 | 20¢/s · 1080p |
| MiniMax | minimax-h3 | 6¢/s · 768p |
Calling an image model through Hedra is one line.
Higgsfield's Soul and an open-weight model on Hedra's engine take the same prompt. Switching is the endpoint and the key.
POST api.higgsfield.ai/higgsfield-ai/soul/v2/standard
Authorization: Key $HF_API_KEY_ID:$HF_API_KEY_SECRET
{ "prompt": "Editorial portrait in soft daylight" }One provider, one model, credits from a bundle.
POST api.hedra.com/v3/models/flux-dev
Authorization: Key $HEDRA_API_KEY
{ "input": { "prompt": "Editorial portrait in soft daylight",
"aspect_ratio": "3:4" } }Open weights on Hedra's engine, billed per megapixel, on Hedra's clusters or yours. Post-train it if the look needs to be yours.
FAQs
- How do Hedra and Higgsfield fit together?
- Higgsfield is a creative product and gateway: presets and credit bundles over partner video models, plus its own Soul image model. Hedra is a layer down: GPU clusters, the inference engine, and post-training for customers.
- 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 Hedra post-train a model for us?
- Yes. Hedra runs supervised fine-tuning, LoRA training, and GRPO on models you own or license, on your data and against your evals, then serves the result on the same engine. The weights are yours.
