Origami documentation
Every model, one OrigamiAI API.
One key, one endpoint, and clear controls for model access, routing, and spend.
One gateway, every model.
- Every model, one API. Text, image, audio, and video share the same key and account controls.
- Drop-in compatible. Change the base URL and key while keeping your established client.
- Usage controlled. Apply model rules, hard budgets, quotas, and full request accounting.
- Managed routing. Stable public model IDs stay independent from routing configuration.
Get your API key
- Open the Origami Console and sign in — or create a workspace.
- Go to API keys and create a key. Keys are scoped per project.
- Copy the key — it is shown once, prefixed
ori_.
Choose a model
Every model on Origami is reachable through the same endpoint — just change the model field. Here are a few currently available text models:
Authentication and key policy
Every public API request is authorized against the virtual key and its active policy.
Bearer authentication
Use Authorization: Bearer $ORIGAMI_API_KEY. The Messages endpoint also accepts x-api-key as an alternative credential.
Server-enforced policy
Activation, expiry, rotation grace, revocation, model rules, modality permissions, CIDR restrictions, budgets, and quotas are evaluated before routing.
List available models
1curl "https://origamiai.my/v1/models" \2 -H "Authorization: Bearer $ORIGAMI_API_KEY"
A key only sees active public models permitted by its account and access policy.
How the API system works
Each request follows a consistent lifecycle from authorization through usage recording.
Validate the virtual key and confirm the requested model and capability are available.
Check the request against the key's active usage, budget, and concurrency limits.
Send the request to an available model service that supports the required capabilities.
Return the response and update the request's usage and cost record.
Models, routing, and capabilities
GET /v1/models.Origami maintains compatible request, response, usage, and streaming behavior across its supported client formats.
Usage, budgets, and accounting
Origami checks limits before a request and records its usage and final cost.
The request is checked against the available balance and every active limit.
Text, cache, media, audio, file, and request usage is recorded when applicable.
The dashboard shows the request status, measured usage, and resulting cost.
If exact usage is unavailable, the cost may be marked as estimated. View request-level details in Usage.
Limits, idempotency, and reliability
Idempotency-Key with 1–255 printable ASCII characters. Keys are scoped to virtual key and endpoint.X-Request-ID when contacting an administrator or investigating a failure.Rate-limit response headers
1RateLimit-Limit: 602RateLimit-Remaining: 423RateLimit-Reset: 184RateLimit-Policy: 60;w=60;comment="key"5X-Request-ID: req_...