TypeLLM
- Family
- TypeLLM
- Released
- 2026-09-20
- Context
- 128K
- Specialization
- general
- Openness
- Proprietary
- License
- ProprietaryRestricted
- Weights
- Not released
- Code
- Unknown
Document AI (PageIndex) and type-safe workflow inference (TypeLLM).
Cheapest of 1 route · TypeLLM
About
TypeLLM is Vectify AI's hosted workflow model. Instead of chat messages, a request declares a context and up to 64 typed questions (strings, numbers, booleans, choices, objects, arrays or image boxes) with dependencies and conditions; TypeLLM plans the graph, runs independent questions in parallel from one shared context and returns every answer in its type in a single API call. Choice, boolean and score questions can return a probability for each option and a confidence. Questions can optionally think before answering, with up to 4,096 reasoning tokens each. Input is text plus up to 8 images, up to 128K tokens.
Providers(1)
Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| TypeLLM | $0.050 | Free | Serverless |
Capabilities
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
typellm-latestDocument AI (PageIndex) and type-safe workflow inference (TypeLLM).
Cheapest of 1 route · TypeLLM