Move from a video prompt generator to a full visual agent
Runway turns prompts into clips through a gateway to other makers' models. Hedra Agent and Workspaces plan, generate, and edit whole projects across video, image, and audio, on GPU infrastructure and an inference engine that Hedra runs itself.
export HEDRA_API_KEY="<key_id>:<secret>"
curl -X POST \
"https://api.hedra.com/v3/models/kling-v3" \
-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": 5000,
"quality": "pro"
} }'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 Runway: focus at a glance
Runway resells models it does not train or serve itself, wrapped in editing tools. Hedra serves models on its own engine and clusters, and post-trains them for customers.
| Dimension | Hedra | Runway |
|---|---|---|
| What it is | GPU infrastructure, inference and post-training research | A model gateway and video editing suite |
| Core technology | Hedra's inference engine, its own GPU clusters, and post-training (SFT, LoRA, GRPO) | Gen-4.5 and an API that fronts Veo 3.1, Seedance 2.5, Hailuo 3 and others |
| Models | Open-weight models on Hedra's engine, models post-trained for you, and partner models through a gateway | Its own Gen models plus third-party models it resells |
| How you connect | API, SDK, CLI, MCP, and Hedra Workspaces | Runway app and the Runway API |
| Where inference runs | Hedra's GPU clusters, or your own | Runway's cloud and its providers' clouds |
| Best fit | Teams building visual products who need inference, capacity and custom models | Filmmakers and creative teams who want shot-level tools |
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 |
Moving a video call to Hedra is one line.
Same prompt, same shape of request. Change the endpoint and the key.
POST api.dev.runwayml.com/v1/text_to_video
Authorization: Bearer $RUNWAYML_API_SECRET
X-Runway-Version: 2024-11-06
{ "model": "gen4.5", "promptText": "A slow dolly
through a rain-lit Tokyo alley at night",
"ratio": "1280:720", "duration": 5 }A gateway call: Runway forwards to whichever provider serves the model, on that provider's terms.
POST api.hedra.com/v3/models/kling-v3
Authorization: Key $HEDRA_API_KEY
{ "input": { "prompt": "A slow dolly through
a rain-lit Tokyo alley at night", ... } }The same request runs open weights on Hedra's engine or a partner model, on Hedra's clusters or yours.
FAQs
- How do Hedra and Runway fit together?
- Runway is a model gateway with a creative suite on top: its API serves Gen-4.5 alongside Veo, Seedance and Hailuo from other makers. Hedra is a layer down. It operates GPU clusters and the inference engine models run on, and post-trains models 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.
