Exa 3.0 highlights make search agents more accurate while using 95% fewer tokens
gaganghotra_ · x · 2026-10-20
Search AI company Exa announced the highlights feature in Exa 3.0: instead of extracting snippets per page, the new model selects tokens across all results, allocating more to the best pages and cutting repeated information. Exa says this makes agents more accurate on search tasks while using 95% fewer tokens than full text — a direct cost and accuracy win for developers building search-powered agents.
Related event: Exa 3.0 Launches, Claiming Top Scores Across All Search Benchmarks(3 posts)→
More from Models
- Anthropic uses Claude to formally verify security properties in 100+ open-source libraries at RISC-V assembly level — AnthropicAI · 2026-10-23
- Are models in an uncanny valley? Researcher warns users to stay vigilant — danielrock · 2026-10-23
- Uncensored Swift 1.5 Qwen 3.8 Flash Next Released as 4-bit GGUF with Strata-Ready Artifacts — jjusko20 · 2026-10-23
- Rumor: Anthropic training a model matching OpenAI's internal one; big launches in December — imjustnewatai · 2026-10-23
- AI researcher: Claude finally finished tedious research tasks I gave up on years ago — MikePFrank · 2026-10-23
- Dream Labs emerges from stealth with Dream-1 robot foundation model at $3/hour — scott_e_reed · 2026-10-23