Model Stacks
A model stack is a preset of three AI models: a primary model and two fallbacks. If the primary is unavailable or rate-limited, your bot automatically tries the next one — no downtime, no config changes needed.
Stacks at a glance
Free models only. Explore without spending a credit.
Efficient paid models. Quality stays high, spend stays low.
Balanced quality and speed for everyday work.
The best models available. For when quality is everything.
How we choose models
Every stack has different criteria. We cross-reference PinchBench (real-world task success rates and cost-per-run value scores) with OpenRouter (live pricing, throughput, availability) before making any changes.
| Stack | Capability bar | Cost bar |
|---|---|---|
| Wanderer | Solid task completion | Must be :free on OpenRouter |
| Hustler | High success rate, strong value score | Lowest cost-per-run with acceptable quality |
| Professional | High success rate, fast throughput | Mid cost — latency matters here |
| Operator | Best available, leads on reasoning | Cost is secondary |
Model details and benchmarks
Competitive with paid frontier models on coding. 1M context, tool calling, 600 req/min with no daily cap.
Google's open multimodal model. Strong general capability, 140+ languages, function calling.
Proven free fallback. Consistent task completion across benchmark runs.
Optimised for ultra-low latency and cost efficiency. Built-in reasoning via API.
PinchBench rank 4 overall. 85.7% task success at $0.15/run — value score nearly double Gemini 2.5 Flash.
Reliable OpenAI fallback. Consistent availability and broad task coverage.
Advanced reasoning with built-in thinking. Top weekly model on OpenRouter. Strong across coding, maths, and science.
Near-frontier intelligence at low latency. Matches Sonnet 4 on reasoning, coding, and computer use.
Lightweight OpenAI fallback. Reliable last resort.
Frontier performance across coding, agents, and professional work. Leads on instruction-following and complex reasoning.
Google's flagship. Strong multimodal reasoning. Preview model — watch for stable release.
Battle-tested flagship. Broad capability across all task types.
How fallback works
Your bot tries models in order. If the primary is unavailable or rate-limited, it moves to fallback 1, then fallback 2. This happens silently — you won’t notice unless you’re watching closely.
Credit usage
Costs vary by model and message length. Rough per-message estimates:
| Stack | Typical cost per message |
|---|---|
| Wanderer | $0 |
| Hustler | $0.001–$0.005 |
| Professional | $0.003–$0.015 |
| Operator | $0.015–$0.08 |
Check your Dashboard usage tab to monitor actual spend.
Switching stacks
Open your Dashboard, go to Settings, and select a new stack. The change applies immediately — no redeploy needed. You can also ask your bot to use any individual model for a specific conversation without changing your stack.