Create a scoped key
Generate a server-side key in the dashboard with rate, token, cost, and model limits before it reaches production.
VIABLE Lab Developer Platform
One API for chat, VETTING, and multimodal AI, built for learning.
A single model-first API with OpenAI-compatible request shapes. Ship tutoring assistants, classroom tools, and learning-science experiments with verified responses, scoped keys, and request-level tracing, end to end.
curl https://api.viablelab.org/v1/chat/completions \
-H "Authorization: Bearer $VIABLE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "viable-2",
"messages": [
{ "role": "user", "content": "Explain photosynthesis to a 5th grader." }
]
}'Every call is traceableRequest ID, model, token usage, and estimated cost land in your dashboard.
BuildIntelligent tutoringAutomated feedbackAnswer verificationLearning analyticsContent generationResearch experiments
Capabilities
Everything you need, behind one base URL.
Chat, verified educational responses, multimodal input, embeddings, media generation, and audio share a single catalog, one auth model, and consistent logging.
Chat & reasoning
OpenAI-compatible chat completions with model-first routing, streaming, and multimodal content arrays.
VETTING
A verification layer over any chat model. Draft, verify against guidance or an answer key, and retry until it passes.
Multimodal input
Send text, images, files, and PDFs as content parts to models that support them, with provider conversion handled for you.
Embeddings
OpenAI-compatible vectors for retrieval, semantic search, clustering, and reranking pipelines.
Image generation
Text-to-image generation with familiar Images-style request shapes across supported providers.
Speech & transcription
Generate speech from text or transcribe uploaded audio with OpenAI-compatible audio endpoints.
Signature capability
VETTING: generation you can actually trust.
VETTING isn't a model. It's a verification architecture layered on top of any chat model. A model drafts a response, a verification pass checks it against your guidance or answer key, and it retries until it passes or hits your attempt limit.
Guide without giving it awayTutor-style answers that won't reveal the homework solution.
Answer-key verificationCheck responses against reference answers with structured, auditable attempt records.
Mix providersUse different chat and verification models across OpenAI, Google, or VIABLE Lab.
1DraftChat model generates a candidate response.
2VerifyA verification pass scores it against guidance or answer key.
3Pass or retryReturn when it passes, or retry with feedback up to your limit.
Built for humans and agents
An agent-native developer workflow.
Whether you're wiring up a classroom tool, a product feature, or a research pipeline, and whether you write it by hand or vibe-code it with an agent, every step is supported, from the first key to a traced request.
Pick the right shape
Choose chat, VETTING, embeddings, images, or audio. Keep request bodies minimal and OpenAI-compatible.
Hand off to your agent
Paste the maintained agent guide into Claude Code, Codex, Cursor, or Gemini CLI and let it build against real docs.
Trace every request
Confirm status, model, usage, estimated cost, and request IDs in logs, while content stays redacted by default.
Agent context
Building with a coding agent?
Drop the maintained API guide into Claude Code, Codex, Cursor, Gemini CLI, or your vibe-coding workflow. Your agent builds against real VIABLE Lab endpoints, with accurate request shapes, model IDs, and VETTING workflows, instead of guessing.
CodexClaude CodeGemini CLICursorWindsurf
Open the agent guide I am building an integration on the VIABLE Lab API. Read the guide at https://developers.viablelab.org/agents/viablelab-api.md and use it as the source of truth. The base URL is https://api.viablelab.org, and protected calls use a VIABLE Lab API key sent as a Bearer token. Follow the documented endpoint shapes, full model IDs, supported aliases, and VETTING workflows. Help me build my own application against this API.Developer operations
A dashboard that runs alongside production.
Create and scope keys, watch usage roll up by key and model, and trace any request down to its raw, redacted payloads, without leaving the portal.
Scoped API keysRate, token, cost, and per-model limits with pause, resume, and revoke.
Usage & costRequests, errors, tokens, and estimated cost over your selected window.
Request logsFilter by key, endpoint, model, status, or platform and export what you need.
6
Endpoint families
3
Model providers
100%
Requests traced
∞
Scoped keys
The API surface
Pick the endpoint that matches the job.
/v1/chat/completionsPOST
General chat, reasoning, multimodal, and streaming.
/v1/chat/vettingPOST
Lightweight vetted chat with verification metadata.
/v1/vetting/fullPOST
Structured answer-key verification workflows.
/v1/embeddingsPOST
Vectors for retrieval and semantic search.
/v1/images/generationsPOST
Text-to-image generation.
/v1/audio/*POST
Speech synthesis and transcription.
Start building in minutes.
Sign in, create a scoped key, and make your first traced request, for a product, a prototype, or a research study.