local-first · v0.1

OpenAI

GPT family models + Responses/Assistants APIs.

llmactiveenterprise-ready#8bb6552d

Supported adapters (this provider can fulfill)

One adapter supports many providers. The default is switchable without changing any workflow.

Served capabilities (derived via adapters)

embeddingllmreasoningspeechvision

Authentication & secrets

authenticationapi_key
auth note—
required secretsOPENAI_API_KEY
permissions—

Secrets are referenced by name only — never values. This runtime performs no OAuth and stores no credentials.

Approval & compliance

requires approvalfalse
approval kinds—
complianceSOC2
enterprise readytrue

Pricing

modelper_token
unitUSD / 1K tokens
note—

Latency & limits

latencymedium
max concurrency—
rate limit / min—
quotaunbounded (request)

Availability & regions

globaltrue
regionsglobal
healthunknown

Deployment targets (without redesign)

laptopmacwindowslinuxhybridawsazuregcpcloudflareenterprise
execution modesapi, cloud

Dependencies & future dispatch

depends on—

Providers describe themselves only. Selection and execution are owned by the future Dispatch Runtime — this layer dispatches nothing.