B3IQ is endpoint-first. Developers call HTTP APIs directly. The official developer surface is endpoint behavior, OpenAPI specs, examples, stable error codes, and public protocol metadata.

No proprietary SDK

B3IQ doesn't ship its own client library or adapter — the hosted gateway is OpenAI-compatible, so the official openai SDK (Python and JavaScript) and any OpenAI-compatible tooling work against it with just a base URL and key swap. See OpenAI SDK Quickstart.

API Families

OpenAI SDK Quickstart

Point the official Python or JavaScript OpenAI SDK at the hosted gateway — chat completions, streaming, and models.list().

Learn More
Hosted Gateway

Public /v1/api/models, /v1/api/stats, and /v1/api/pricing, plus authenticated OpenAI-compatible /v1/api/chat/completions backed by B3IQ router, metering, and receipt policy.

Learn More
Local Host Agent

Local OpenAI-compatible endpoints and node companion APIs served at http://127.0.0.1:8831 by default.

Learn More
Private Jobs

B3IQ-native async encrypted job APIs for private transport workflows.

Learn More
Receipts And Payouts

Receipt lookup, settlement status, dashboard usage views, and payout evidence surfaces.

Learn More
b3iq CLI

Manage your machines, models, runtimes, and SSH access from the terminal or a script — the same account credentials as the HTTP APIs.

Learn More

OpenAI-Compatible Endpoint Matrix

SurfaceEndpointAuthNotes
Hosted metadatahttps://b3iq.org/v1/api/modelsNonePublic OpenAI-compatible model list
Hosted metadatahttps://b3iq.org/v1/api/statsNonePublic aggregate network stats
Hosted metadatahttps://b3iq.org/v1/api/pricingNonePublic quote and node-payout policy
Hosted gatewayhttps://b3iq.org/v1/api/chat/completionsHosted gateway keyFree routed inference on your own machines, with metering, receipts, and route policy
Local host agenthttp://127.0.0.1:8831/v1/chat/completionsLocal `b3iq_local_` keyLocal machine inference through the host agent
Native private jobshttps://b3iq.org/v1/api/private-inference/jobsCustomer headersB3IQ-native encrypted async work, not OpenAI-compatible

Credential Separation

SurfaceCredentialNotes
Local host-agent chatb3iq_local_Local-only scoped key created by the owner in the setup wizard
Hosted gateway chatb3iq_gateway_Gateway key that carries account ownership and usage attribution
Native private jobscustomer headersCustomer ID and token headers for B3IQ-native job creation and settlement reads
Setup and local adminowner session or setup tokenLocal operator UI and setup APIs, not normal application credentials
b3iq CLI and automationb3iq_pat_Personal access token minted by `b3iq login` or Settings → CLI tokens; shown once, revocable

Base URLs

bash
export B3IQ_GATEWAY_BASE_URL="https://b3iq.org/v1/api"export B3IQ_LOCAL_BASE_URL="http://127.0.0.1:8831"

Use the public hosted gateway base URL for unauthenticated metadata and authenticated hosted work. For local node work, use the host-agent URL on the machine running B3IQ.

Request Safety Pattern

1

Store keys in files

bash
umask 077mkdir -p .secretscat > .secrets/b3iq-gateway-keycat > .secrets/b3iq-local-key
2

Pass auth through a short-lived config

Avoid placing bearer tokens directly in shell argv.

3

Send request bodies through stdin

This keeps examples readable and avoids local files that accidentally include prompts, outputs, or secret material.

OpenAPI Specs

Hosted Gateway OpenAPI

Hosted OpenAI-compatible chat/models plus B3IQ-native private job, receipt, billing, and public surfaces.

Learn More
Local Host-Agent OpenAPI

Local health, chat, models, model profiles, receipts, and receipt submission.

Learn More

Public Privacy Rule

Prompts, outputs, exact private routes, API keys, customer identity, local URLs, filesystem paths, raw request logs, raw tokens, and raw TEE quotes do not belong in public docs examples, public protocol payloads, or settlement metadata.

Ask a question... ⌘I