Developers

Build on Auvryn

Everything in Auvryn is available through a REST API described by a public OpenAPI 3.1 document. Executions are asynchronous: you create an ExecutionJob, follow its status, then read its verified result and provenance.

Auvryn is provider-neutral execution infrastructure for AI models. It validates ONNX models, runs them as durable ExecutionJobs on infrastructure it does not own, and returns verified results with provenance and telemetry.

The Developer API

Base URL: https://api.auvrynspace.com/api/v1
Description: OpenAPI 3.1, public: https://api.auvrynspace.com/api/v1/openapi.json
Authentication: API keys sent as a Bearer token. Keys carry scopes, can be limited to one project, expire, and are stored only as hashes.
Creates: Idempotent: send an Idempotency-Key header and a retried request never creates a second resource.
Errors: One error envelope with a stable code and a request ID; resources of another workspace answer “not found”.

The asynchronous flow

Create a model and a version, then upload the ONNX file to the signed URL the API returns.
Request validation; optionally run a sandbox test.
Optionally define an area of interest and ask a provider for a cost estimate.
Create an ExecutionJob for a provider; poll it until it is final.
Read the result: its artifacts, their SHA-256, and the execution’s provenance and telemetry.

Interfaces

The web app and the REST API are available in early access. A TypeScript SDK, a CLI with exit codes for CI pipelines, and an MCP server that lets an AI assistant drive the same workflow are built on the API; they are 0.x, not yet published, and design partners get them directly.

For agents and tools

Auvryn publishes what a program needs to discover it without reading prose.

/.well-known/api-catalog: The API catalog (RFC 9727): where the API, its OpenAPI description and its documentation live. https://auvrynspace.com/.well-known/api-catalog
/capabilities.json: A small, versioned description of what Auvryn supports today: model formats, interfaces, execution model, environments and whether each is simulated or real, provenance and telemetry, availability and restrictions. https://auvrynspace.com/capabilities.json
OpenAPI 3.1: https://api.auvrynspace.com/api/v1/openapi.json

Current limits

Model format: ONNX.
Execution: asynchronous jobs only; there is no synchronous inference endpoint.
Providers: you choose the provider for each job; Auvryn does not pick one for you.
Access: early access; there is no public pricing yet.

Facts reviewed 2026-10-07.