Start a project
Organize credentials, environments, model access, and usage boundaries.
05 / DEVELOPERSRAYA.COM.AI
Build Indonesian AI into real products.
RAYA gives developers a direct path from localized model selection to production tokens, with familiar API patterns and enterprise-ready controls.
POSITION
A local model only matters when developers can use it reliably inside products, workflows, and customer experiences.
QUICKSTART / REQUESTAPI.RAYA.COM.AI/V1
01
02
03
04
05
06
07
08
02
03
04
05
06
07
08
curl https://api.raya.com.ai/v1/responses \
-H "Authorization: Bearer $RAYA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "raya-local",
"input": "Summarize this Indonesian report."
}'RESPONSE200 / STREAMLocalized model outputUsage returned by token
PLANNED API CONTRACT
A predictable path to production
AuthenticationBearer project keyScoped by environment
Generation/v1/responsesStreaming + structured output
Embeddings/v1/embeddingsRetrieval + semantic search
UsageInput / output TokensReturned per response
ErrorsConsistent status modelRequest ID for support
VersioningStable model identifiersDocumented migration window
This interface describes the intended developer experience. Final endpoints, SDKs, limits, and availability will be confirmed before public access.
01 / APPROACH
How it works
Call the API
Use generation, streaming, structured outputs, embeddings, and tool-oriented patterns.
Test your workload
Measure model behavior on representative Indonesian and business-specific tasks.
Ship with control
Track usage and reliability, then move to dedicated or private delivery if required.
02 / SCOPE
What it includes
API
Consistent model and response interfaces
→SDKs
Developer libraries and implementation examples
→Console
Projects, credentials, usage, and model visibility
→Documentation
Quickstarts, API reference, guides, and enterprise patterns
→03 / QUESTIONS
Frequently asked
How will developers access RAYA models?
Through project-based API credentials, model identifiers, developer documentation, and a console for usage and access visibility.
Which API capabilities are planned?
The platform direction includes generation, streaming, structured outputs, embeddings, and tool-oriented workflows.
Can a prototype move to private deployment?
Yes. The same model and application pattern can be evaluated for dedicated or private delivery as requirements mature.