Tuesday, 21 July 2026 Sign in

Introducing Structured Outputs in the API

OpenAI Blog 6 August 2024, 10:00

Anthropic added Structured Outputs to its API, enabling model responses to reliably conform to developer-specified JSON Schemas. The feature works with Claude 3.5 Sonnet and Claude 3.5 Haiku models. This allows developers to programmatically parse and integrate model outputs without additional validation or error handling.

Why it matters

We are introducing Structured Outputs in the API—model outputs now reliably adhere to developer-supplied JSON Schemas.

Read the full story at OpenAI Blog

Anthropic

Every AI story that matters,
in your inbox by 8am.

TLDRocket reads 60+ sources, removes duplicate coverage, and summarises the day in two minutes. Free, no spam, unsubscribe anytime.

TLDRocket 21 July 2026

The open-weight AI model market hit an inflection point today as Alibaba and Kimi released trillion-parameter competitors that challenge the closed-model orthodoxy—just as Washington moved to restrict them. Alibaba's Qwen 3.8 Max (2.4 trillion parameters) and Kimi K3 (2.8T) are going open-weight, with K3 ranking first on Frontend Web App Arena and fourth on agentic benchmarks, signaling that scale and transparency can coexist. The timing matters: while U.S. policymakers weigh layered restrictions on Chinese open models, technical experts are pushing back hard, arguing that closed gardens actually hurt security and competition more than they help. The real fragmentation risk isn't technical—it's regulatory.

Read the full briefing →

Introducing Structured Outputs in the API

Why it matters

Related stories

Every AI story that matters, in your inbox by 8am.

Every AI story that matters,
in your inbox by 8am.