June 12, 2026
API and MCP: bring Givon AI generation into your apps and agents
Givon AI video and image generation can now be called from code and AI agents. Use the REST API, self-describing model schemas, owner-media assets, and the MCP server behind the same API key.
Givon AI generation can now be embedded into services, internal tools, and AI agents without using the web interface. The release includes a REST API, an MCP server, model discovery, and owner-media assets for references.
The API is built around one generation flow for all image and video models. Fetch the catalog, inspect the fields, limits, and estimated token cost, upload or import assets when needed, then start a generation with the schema-backed input for the selected model.
The MCP server exposes the same model-aware workflow to AI agents. Instead of hard-coding parameters, an agent can read the model schema, prepare a valid request, and call Givon AI through the same account balance.
On this page
What changed
Model catalog
GET /api/v1/models returns model purpose, fields, limits, and estimated cost so integrations do not rely on guesswork.
One generation request
POST /api/v1/generations uses the same shape across models: type, model, and input.
Assets and references
Upload or import media, receive an asset URI, and pass it into model fields that accept references.
MCP for agents
AI agents can discover model schemas and prepare generation requests through the Givon AI MCP server.
Workflow
How the developer workflow works
Start with the catalog endpoint. It gives the available public image and video models, their required fields, supported options, and estimated token use. That catalog is the integration contract, so client code can stay aligned as model options evolve.
For media references, create an owner-media asset first. The returned asset URI can then be used in model inputs for reference images, starting frames, source videos, or other supported fields.
Errors happen before tokens are spent
Inputs are validated against the selected model schema before a generation starts, so malformed requests are rejected before balance is charged.
Agents
Why MCP matters for AI agents
The MCP server lets agent tools call Givon AI with the same account key and the same model definitions as the REST API. This is useful when the agent decides which model fits the task, checks the schema, and assembles the request itself.
Use it for internal content pipelines, creative assistants, marketplace image automation, and workflows where a human should review the result rather than manually repeat the generation setup every time.
FAQ
API and MCP questions
- Where do I create an API key?
- Keys are managed in the Givon AI account, in the developer integrations area.
- Do API generations use the same balance?
- Yes. API and MCP generations use your Givon AI token balance.