Skip to main content
Start with managed inference through the v3 API. Choose a quickstart below; each walks you through creating an API key, funding your API wallet, and making your first request.

Understand images and reason

Send an image and a question. Read the answer directly from the chat API response.

Generate images, video, or audio

Submit a model job, follow its progress, and retrieve the output.
Choose a model and check its inputs, limits, and pricing in the model catalog. To use Hedra from an assistant or your terminal, start with MCP setup or SDKs and developer tools.

​
Docs and console

Use these docs for integration guides, examples, and the API reference. Open the console to try models, inspect jobs, and manage API access and billing. To start an integration, get an API key.

​
From inference to post-training

Hedra’s research and infrastructure connect model adaptation, evaluation, and deployment for real-world workloads. For physical AI models, bringing your own model, or deploying on your own infrastructure, start with Platform and availability and deployment options. World Model Runtime is Hedra’s engine for multimodal workloads. Hedra Training connects model adaptation and evaluation with deployment. GPU Sandboxes provide isolated compute for custom code and pipelines. Training and GPU Sandboxes are currently research previews. See Hedra’s platform overview or contact the engineering team to discuss access and supported workloads.

​
Existing integrations

Building a new integration? Use v3. If you use the /web-app/public API, read Migrate from v2 to v3.