Google Veo and Hedra: a frontier model, and an inference company
Google trains Veo and serves it on Google Cloud. Hedra operates GPU clusters and an inference engine, post-trains models for customers, and serves Veo 3.1 beside open weights through one key.
export HEDRA_API_KEY="<key_id>:<secret>"
curl -X POST \
"https://api.hedra.com/v3/models/veo-31" \
-H "Authorization: Key $HEDRA_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "input": {
"prompt": "A slow dolly through a rain-lit Tokyo alley at night",
"aspect_ratio": "16:9",
"resolution": "1080p",
"duration_ms": 8000
} }'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 Google Veo: focus at a glance
Google builds Veo and serves it on Google Cloud. Hedra is an inference and research company that serves Veo and open weights on one engine.
| Dimension | Hedra | Google Veo |
|---|---|---|
| What it is | GPU infrastructure, inference and post-training research | A frontier video model from a hyperscaler |
| Core technology | Hedra's inference engine, its own GPU clusters, and post-training (SFT, LoRA, GRPO) | Veo 3.1 and the Gemini model family |
| Models | Open-weight models on Hedra's engine, models post-trained for you, and partner models through a gateway | Its own Veo and Gemini models |
| How you connect | API, SDK, CLI, MCP, and Hedra Workspaces | Gemini API, Vertex AI and Google's apps |
| Where inference runs | Hedra's GPU clusters, or your own | Google Cloud |
| Best fit | Teams building visual products who need inference, capacity and custom models | Google Cloud customers and Gemini users |
Veo on Hedra, beside open weights and the other leading video models
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 |
|---|---|---|
| veo-31 | 39.29¢/s · 1080p | |
| veo-3 | 40¢/s · 1080p | |
| veo-2 | 50¢/s · 720p | |
| Kling | kling-v3 | 16.8¢/s · 1080p |
| Alibaba | wan-3-0 | 20¢/s · 1080p |
FAQs
- Is this the same Veo that Google ships?
- Yes. Veo 3.1, Veo 3 and Veo 2 are Google's models, served by Google and reached through Hedra's gateway with the same request shape as every other model in the catalog. Open-weight models run on Hedra's engine beside them.
- 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.
