Internal briefing · October 2026The key skill now is AI delegation: matching each job to the model whose competence, cost profile and personality fit it, the way you'd put the right people on a project.
OpenAI models
Anthropic models
From frontier horsepower down to cheap, narrow decisions.
OpenAI
Frontier intelligence and high technical complexity
Use when
Long-running, tireless work that needs extreme intelligence and predictable execution with custom skills.
Trade-off
Reserve it for jobs that truly need it. Ultra-fast mode burns plan allowance quickly, and without strong steering it makes expensive mistakes fast.
OpenAI
Heavy data synthesis and high-token workloads
Use when
Big projects with massive context: piles of data, code or documents, or computer use. Persistent without draining weekly limits.
Trade-off
Approaches Astra on some benchmarks at about one-fifth of the token price. Shade task complexity slightly down.
OpenAI · Decisions API
Fast, cheap classification
Use when
Constrained "Type 1" decisions: tagging incoming email, sorting customer records, classifying changes by pricing or release date.
Trade-off
Built for narrow decision structures, not open-ended writing. That focus is what makes it so fast and cheap.
Insight, writing quality and dependable structured execution.
Anthropic
Intuitive synthesis and pattern discovery
Use when
Deep qualitative analysis across messy, massive archives, like months of transcripts and long documents, where people can't see the forest for the trees.
Strength
Finds patterns you didn't know to look for, pulls new insight straight from sources and explains it in clear, well-written prose.
Anthropic
High-quality, natural writing
Use when
Producing a large volume of clean, high-quality written work, and you can give the model time to work.
Strength
Very responsive to steering away from stiff, mannered prose. Slower to generate than Astra.
Anthropic
Efficient, structured execution
Use when
Well-defined, structured tasks with moderate to high complexity.
Strength
Priced the same as Sol. A dependable, highly competent workhorse that reliably gets through the work.
Each model rated 1–5. Cost uses published API prices; speed uses measured throughput where it exists.
| Model | 🧠Brainpower | $CostAPI price, in / out per 1M | 🏃Speed | Best at |
|---|
Context size isn't a differentiator. All six models now take roughly 1 million tokens of input and return up to 128K. Choose on brainpower, cost and speed instead. On OpenAI models, a single request over 272K input tokens is billed at double the input rate.
A routing guide with a sample Saratoga prompt for each. Copy one and adapt it.
AstraSolLunaFable 5.1Opus 5.5Sonnet 5.5Ask what the task needs: depth, volume, speed or a narrow decision. Then pick the model that fits.
The most capable model is also the fastest way to burn budget. Save it for work that would fail without it.
Stronger models move faster in both directions. Clear instructions and checkpoints keep mistakes cheap.