Quickstart

Make your first traced API call.

Create a dashboard key, keep it out of client code, call the endpoint that matches the job, then verify the request in logs. Use a direct endpoint for simple calls, or publish an agent when the workflow needs multiple coordinated steps.

Create API keyBrowse API reference
1 · Create keyScope the key before production.2 · Pick shapeDirect endpoint or published agent.
3 · Send requestOr test first in the Playground.
4 · Check logsConfirm status, usage, and request ID.

Before you begin

Keep the key out of client code

Create a VIABLE Lab API key, then load it from your app's secret store, environment manager, or backend config. The examples use <VIABLE_API_KEY> as a placeholder.

Create or reveal key

Agent context

Building with a coding agent?

Drop the maintained API guide into Claude Code, Codex, Cursor, Gemini CLI, or another AI-assisted workflow. Your agent can use direct endpoints when they fit, or draft VIABLE Lab agent workflow JSON when you need orchestration.

Codex Claude Code Gemini CLI Cursor Windsurf
Open the agent guide
Prompt
I am building with the VIABLE Lab API. Read https://developers.viablelab.org/agents/viablelab-api.md as the source of truth. Prefer direct endpoints for one-step chat, VETTING, embeddings, image, speech, transcription, or encryption; suggest Dashboard Agents only when a product flow needs branching, loops, or multiple coordinated model/tool calls behind one endpoint. Auth uses Bearer VIABLE Lab API keys with endpoint scopes such as model:request, utils:crypto, and agents:execute. For published agent runs, call POST /v1/agents/{slug}/runs and persist conversation_id per end-user thread + agent slug; run_id is one execution and request_id is for log/support correlation. Treat any direct-endpoint or provider-level session state as separate from this agent conversation_id.

General

/v1/chat/completions

Educational

/v1/chat/vetting

Structured

/v1/vetting/full

Orchestration

/v1/agents/{slug}/runs

Retrieval

/v1/embeddings

Media

/v1/images/generations

Audio

/v1/audio/*

First request

OpenAI Python SDK

OpenAI-compatible endpoints work with OpenAI SDKs by setting the base URL to https://api.viablelab.org/v1.

OpenAI Python SDK
from openai import OpenAI

client = OpenAI(
    base_url="https://api.viablelab.org/v1",
    api_key="<VIABLE_API_KEY>",
)

response = client.chat.completions.create(
    model="viable-2",
    messages=[
        {"role": "user", "content": "Explain how AI works in one sentence."}
    ],
)

print(response.choices[0].message.content)