According to TechCrunch and The Verge, OpenAI presented benchmark results for Jalapeño, its custom AI inference chip, showing higher tokens-per-user throughput and better efficiency (tokens per kilowatt) than Nvidia's Blackwell system on SemiAnalysis' InferenceX benchmark. OpenAI hardware head Richard Ho said Jalapeño "can serve more AI work per unit of power, while also returning responses more quickly." The company expects limited deployment by end of 2026, with wider availability in 2027.
Topics #
Sources #
- Press
[TechCrunch](https://techcrunch.com/2026/08/25/openais-jalapeno-chip-is-built-for-fast-inference-at-scale-benchmarks-show/) - Press
[The Verge](https://www.theverge.com/ai-artificial-intelligence/984290/openai-jalapeno-ai-chip-benchmarks)
This intelligence is sourced automatically from public sources across the web and synthesised by the Prefactor AI pipeline. Stories are reviewed before publication.
source & further reading
getreadyforagents.com — original article
OpenAI releases ChatGPT Work at $20/month tier to move AI agents from developers to white-collar workers
Instinct AI assistant raises privacy and security concerns in private testing due to broad data access
OpenAI cuts GPT 5.6 Sol pricing by 20% through at least November 2026