Vercel AI Gateway launches Evaluation API returning structured judgments, not free-form text
zeeg · x · 2026-09-20
Vercel announced that its AI Gateway now supports Evaluation, callable via HTTP or the TypeSafe SDK.
- Evaluation models answer typed questions against shared state, returning choices, scores, and boolean probabilities (e.g. refunded: {probability: 0.99}) instead of free-form text — suited to classification, routing, rubric-based assessment, and automated verification
- Multiple questions can be answered in parallel in a single request against the same state
- Requires AI SDK 7+ (via experimentalevaluate) or the HTTP/TypeSafe-compatible API; OpenAI-, Anthropic-, and Cohere-compatible endpoints are not supported
More from coding & agent
- Blender previs + Hailuo H3: a workflow for AI-rendered architectural animations — Hailuo_AI · 2026-09-20
- Parallel-sampling decision model Jev routes in ~1s vs 4-14s for regular LLMs — TigerOk4538 · 2026-09-20
- Dev builds fully autonomous trading bot in a day — it has already lost him $31,680 — ZeYanjie · 2026-09-20
- Three coding habits that may never come back in the AI-agent era — BLUECOW009 · 2026-09-20
- mcp-proxmox lets you manage Proxmox VE clusters with natural language — modelcontextprotocol · 2026-09-20
- Tronsave MCP Testnet lets agents buy and sell TRON resources via one interface — modelcontextprotocol · 2026-09-20