Grok 4.7 hits Amazon Bedrock: 500K context, 2x output tokens for the gains
AWS ML Blog · rss · 2026-09-29
AWS ML Blog details xAI's Grok 4.7 on Amazon Bedrock: 500K token context, four reasoning-effort levels, and Responses/Chat Completions/Converse APIs. Trained with longer RL on harder tasks, it emphasizes self-verification for long-horizon agents. Artificial Analysis scores it Intelligence Index 46 (vs 44), Coding Agent 56 (vs 47), hallucination rate down to 29% — but output tokens roughly doubled (81K/task). Ships with a new safeguard stack (strongest refusals/jailbreak resistance xAI has tested). On Bedrock: cross-region inference profiles, OpenAI SDK compatibility, implicit prompt caching, Guardrails, structured outputs, and default/priority/flex service tiers.
More from Infra
- Google Cloud: Startups should pair open models with frontier APIs in four key workloads — rseroter · 2026-09-29
- Chronos DB: a Postgres-compatible database that gives each agent a 2-microsecond branch and human-reviewed merges — Antique-Willow-5841 · 2026-09-29
- Silicon photonics is a 'difficult on difficult' problem: ICs, packaging, fiber attach and test combined — BenBajarin · 2026-09-29
- Stillcore invests in Lium (Bittensor Subnet 51), renting H100s from $2.43/GPU-hour — markjeffrey · 2026-09-29
- Workstation with RTX PRO 4500 Blackwell 32GB: what local models can I run comfortably? — Musicheardworldwide · 2026-09-29
- Weaviate Podcast: split database duties between Postgres for structured data and vector search — CShorten30 · 2026-09-29