OpenRouter
First met in aicp-c3-basecamp-03 · Models & model access
OpenRouterFirst met in aicp-c3-basecamp-03 · Models & model access
One API key and one endpoint in front of hundreds of models — switch model without switching integration.
You want to change models freely (or fall back automatically) without rewriting credentials in every workflow.
Rankings and side-by-side model comparison pages that show what's actually being used
A single credential in an n8n agent node covers every model it fronts
Makes model choice a runtime decision rather than an architectural one
Routes requests to hundreds of hosted models through one API
Exposes rankings and price/perf comparisons for picking
Serves as the chat-model credential inside automation platforms
Doesn't host models itself — it's a router, so upstream outages are still outages
Doesn't beat a direct vendor key on price for a single model you've settled on
The model-access layer of any agent build where you expect to experiment, benchmark, or switch as prices move.
Models & model access
Nothing in the pipeline calls models by API yet.
The right first stop if the SQLite/vector phase needs an embedding or summarization API — one key, easy to benchmark alternatives against.
current
ollama: hosted-and-flexible vs local-and-free
n8n: one credential for every agent node
| Session | Coverage | Moment | What happened |
|---|---|---|---|
| Basecamp 3: Introduction to n8n — I | demonstrated | 1:35:00 | Rankings and model-compare pages toured; positioned as the single-API model switcher for agent nodes |
| AI Sprint: Claude Code with Antigravity — Day 1 (Taste as the Moat, the Muscle-and-Mirror Setup, and the Model Council Build) | demonstrated | The council's model layer; live catalog checks correct the agent (Gemini 3.1 Pro, Grok 4.2); ':online' suffix adds web search; $0.26 total | |
| AI Sprint: Claude Code with Antigravity — Day 2 (CLAUDE.md, the 50% Context Rule, and the Sketch-to-App Build) | demonstrated | User-selectable vision models behind the key-protecting server route | |
| AI Sprint: The Hermes Agent — Day 1 (Always-On Agents, the Employee-on-Day-One System, and the Self-Improving Ghostwriter) | demonstrated | Hermes' provider (Opus 4.6 for price); also the image-generation route; credits checked mid-debug | |
| AI Sprint: The Open Source Playbook — Day 1 (Licenses, Open Weights, and Why Open Isn't Free) | demonstrated | BYOK layer for Open Design; the activity page as the cost meter | |
| AI Sprint: The Open Source Playbook — Day 2 (Weights 101, OpenCode, and the Subsidy Math) | demonstrated | The BYOK spine: provider config in OpenCode, per-model activity as the meter | |
| AI Sprint: AI Evals & Reliability — Day 2 (Testing Systems That Never Answer Twice) | demonstrated | BYOK keys powering the support bot's multi-model orchestration | |
| AI Sprint: Windsurf & Devin — Day 2 (Building Superplexity: Plan with Opus, Execute with Cascade, Review with Devin) | demonstrated | Sonnet 4.6 for synthesis, Sonar for search, keys in .env — 'I won't face rate limits because I'm using OpenRouter' | |
| AI Sprint: The Hermes Agent — Day 2 (Loop Engineering: the Scheduling Loop, the Delegation Loop, and the Skill Auditor) | explained | The catalog for the cheap-model lane (DeepSeek, Kimi, open models); fallback chains |