Microsoft's decision model for sorting requests, choosing a route and scoring results without generating a chat response.
- Input price
- $0.042 / 1M input tokens; output free
- Input capacity
- 32,768 tokens
Resources
Top AI Models for Typed Decisions
Decision models turn text or structured state into bounded choices, scores, probabilities, and routing signals for software. Compare price, input capacity, question shapes, output contracts, uncertainty, and API access.
Showing 1–4 of 4 models
Cloudflare · Live
Clef
Cloudflare's larger decision model for classifying information and choosing an action without generating a chat response.
- Input price
- $0.24 / 1M input tokens
- Input capacity
- 65,536 tokens; up to 64 questions per request
Cloudflare · Live
Clef-flash
A smaller Cloudflare decision model for frequent routing and classification tasks, with a lower input-token price than Clef.
- Input price
- $0.038 / 1M input tokens
- Input capacity
- 24,576 tokens on Workers AI; up to 64 questions per request
TypeSafe AI · Live
Jev 1.13
TypeSafe AI's first System One model for fast, typed choices, scores, and probabilities that software can use directly.
- Input price
- $0.042 / 1M input tokens; output free
- Input capacity
- 64K tokens total; state plus longest question up to 32K
What to compare
- Input price
- Current provider price for the text or structured state submitted to the model, including whether decision outputs are billed.
- Input capacity
- Maximum documented state and question capacity for one request.
- Decision types
- The bounded question forms the model can answer, such as choices, scores, or probabilities.
How to use this library
Compare the job, not the hype.
A curated cross-category set of frontier, specialist, and category-defining models with practical API information for real product decisions.
Cody does not run a universal quality leaderboard. Provider claims are labeled, pricing excludes taxes and optional tools, and production buyers should verify the live provider terms before choosing a model.
- 01
Use first-party documentation for technical limits, lifecycle, pricing, regional access, and data policies whenever it exists.
- 02
Compare models only inside the same category and retain each provider's measurement basis.
- 03
Show Not published when a provider has not published a comparable fact instead of estimating it.
- 04
Treat prices and availability as dated snapshots and link every page to live provider documentation.
Speed keeps its units
Voice latency, text throughput, video render time, and world-model frame rate are not interchangeable.
Unknown stays unknown
A missing release date, country list, or latency number is labeled as unpublished instead of estimated.
Every fact has a date
Model pages link to the underlying source and show when pricing, access, and policies were last checked.
Put the model to work
Pick the model, then give it a better brief.
Use Cody's expanded prompt playbooks and curated agent skills to turn a model choice into a repeatable workflow.