{"slug": "ai-agents-weekly-claude-haiku-5-5-gemini-agent-mistral-large-4-decisions-api-and", "title": "🤖 AI Agents Weekly: Claude Haiku 5.5, Gemini Agent, Mistral Large 4, Decisions API, Personal Agent Protocol, Devin Dreaming, and More", "summary": "Anthropic released Claude Haiku 5.5, which it calls its cheapest, fastest, and most capable small model to date, priced at $0.10 input and $0.50 output per million tokens for prompts up to 100K tokens — about 75% less to run on average than Haiku 4.5. The model scores 72.4% on the OSWorld 2.1 offline subset versus 15.7% for Haiku 4.5, 39.2% on Terminal-Bench 4.0 versus 0.0%, and a GDPval-AA v2.1 Elo of 1620 versus 735, and is the first Haiku model with an adjustable effort setting. Anthropic also cut Sonnet 5.5 cache reads from $0.20 to $0.10 per million tokens, cutting its cost on most agentic work by around 20%, and added computer use and browser use in beta to its Python and TypeScript SDKs.", "body_md": "In today’s issue:\n\n- Anthropic ships Claude Haiku 5.5\n- Google launches the Gemini agent\n- Mistral previews Large 4\n- OpenAI opens the Decisions API\n- Meta and Sierra propose Personal Agent Protocol\n- Devin gets Memory and Dreaming\n- Reflection unveils Beam open model\n- GPT-6 brings Intelligent UI to ChatGPT\n- Hugging Face trains models across harnesses\n- OpenAI releases 719 math manuscripts\n\nAnd all the top AI dev news, papers, and tools.\n\n## Top Stories\n\n### Claude Haiku 5.5\n\nAnthropic released Claude Haiku 5.5, which it calls its cheapest, fastest, and most capable small model to date. It targets high-volume work such as summaries, compaction, classification, and subagent tasks under Opus 5.5 and Sonnet 5.5, and costs around 75% less to run than Haiku 4.5 on average.\n\n- **Agentic performance:** 72.4% on the OSWorld 2.1 offline subset against 15.7% for Haiku 4.5, 39.2% on Terminal-Bench 4.0 against 0.0%, and a GDPval-AA v2.1 Elo of 1620 against 735.\n- **Pricing:** $0.10 input, $0.50 output, and $0.01 cache reads per million tokens for prompts up to 100K tokens, which covered about 90% of Haiku 4.5 requests. Longer prompts cost $0.50 input and $2.50 output.\n- **Effort control:** It is the first Haiku model with an adjustable effort setting, so developers can trade cost for intelligence per task.\n- **Wider price changes:** Sonnet 5.5 cache reads drop from $0.20 to $0.10 per million tokens, cutting its cost on most agentic work by around 20%. Max and Team subscribers get monthly API credits of $100 to $500, and the Python and TypeScript SDKs add computer use and browser use in beta.\n- **Availability:** Live as`claude-haiku-5-5` on all platforms, including AWS, Google Cloud, and Azure.", "url": "https://wpnews.pro/news/ai-agents-weekly-claude-haiku-5-5-gemini-agent-mistral-large-4-decisions-api-and", "canonical_source": "https://nlp.elvissaravia.com/p/ai-agents-weekly-claude-haiku-55", "published_at": "2026-10-10 14:40:28+00:00", "updated_at": "2026-10-10 16:49:20.908836+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-products", "ai-tools"], "entities": ["Anthropic", "Claude Haiku 5.5", "Haiku 4.5", "Sonnet 5.5", "Opus 5.5", "AWS", "Google Cloud", "Azure"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/ai-agents-weekly-claude-haiku-5-5-gemini-agent-mistral-large-4-decisions-api-and", "markdown": "https://wpnews.pro/news/ai-agents-weekly-claude-haiku-5-5-gemini-agent-mistral-large-4-decisions-api-and.md", "text": "https://wpnews.pro/news/ai-agents-weekly-claude-haiku-5-5-gemini-agent-mistral-large-4-decisions-api-and.txt", "jsonld": "https://wpnews.pro/news/ai-agents-weekly-claude-haiku-5-5-gemini-agent-mistral-large-4-decisions-api-and.jsonld"}}