riva-translate-4b-instruct-v1.1 has been retired
What to do: Requests to riva-translate-4b-instruct-v1.1 now fail. Switch to another model.
AIWire: AI model shutdowns, prices and API changes
The wire
Every change we detect, newest first. Times are Eastern (ET). Archive
MondayOctober 5, 2026
We've added capabilities.thinking.types.disabled to the Models API.
What to do: Update model capability checks to read capabilities.thinking.types.disabled from the Models API when deciding whether to send thinking: {type: "disabled"}.
SaturdayOctober 3, 2026
Getting the most out of Opus 5.5 in Claude and Claude Code
InfoResearchHacker News · community
What to do: Review your prompts and CLAUDE.md files to remove 'think step by step' style instructions and add stop/continue rules before running long tasks on Opus 5.5.
Show HN: Offrun – manage every coding agent from one workspace
InfoReleasesHacker News · community
What to do: No action needed; background reading.
FridayOctober 2, 2026
OpenAI Python SDK 3.24.0
What to do: Update to v3.24.0 to access custom voice creation and agent session events, and to benefit from routing field prioritization fixes.
OpenAI deprecated gpt-5.1: shuts down Apr 1, 2027 (move to gpt-6-sol)
What to do: Move to gpt-6-sol before Apr 1, 2027.
OpenAI deprecated gpt-5.4-nano: shuts down Apr 1, 2027 (move to gpt-6-luna)
What to do: Move to gpt-6-luna before Apr 1, 2027.
OpenAI deprecated gpt-5.3-codex: shuts down Apr 1, 2027 (move to gpt-6-sol)
What to do: Move to gpt-6-sol before Apr 1, 2027.
ThursdayOctober 1, 2026
How to Evaluate Live & Voice Agents in ADK
What to do: Install the ADK eval extras with uv pip install -e ".[eval]" and configure API credentials for both the Live API and Gemini TTS to enable live voice agent evaluation.
Build zero-trust AI agents that judge intent, not just syntax
What to do: Review the new zero-trust runtime governance controls (Model Armor, Semantic Governance Policies, and Agent Anomaly Detection) if you deploy agents to the Gemini Enterprise Agent Platform, and consid…
Agent Anomaly Detection, now in Private Preview on the Gemini Enterprise Agent Platform
What to do: If you deploy agents on the Gemini Enterprise Agent Platform with ADK 1.2 or later, review the documentation for prerequisites and setup to enable Agent Anomaly Detection with one-click provisioning.
Introducing Support for Local AI Models in the Antigravity SDK
What to do: Try local agentic workflows with the Antigravity SDK by following the README instructions, using a machine with >24GB VRAM or unified memory for Gemma 4 26B A4B via LiteRT, or connect your own OpenAI…
Turn your REST APIs into MCP tools with Google Cloud API Gateway
What to do: Annotate your OpenAPI spec with MCP metadata and deploy it to Google Cloud API Gateway to expose existing REST APIs as MCP tools without building a separate server.
OpenAI Python SDK 3.23.0
What to do: Update the OpenAI Python SDK to v3.23.0 to use new Agents features (typed session-stream answers, file staging, turn-artifact downloads, typed application actions as tools, and final-output collectio…
We've added a line field to the Models API.
What to do: Use the new line field to group models instead of parsing model IDs.
WednesdaySeptember 30, 2026
Anthropic Python SDK 1.11.0
What to do: Update to v1.11.0 to access the new list spend limits endpoint and note that sonnet 4.5 is deprecated.
Google Gen AI Python SDK 2.26.0
What to do: Update to v2.26.0 to use new features like GCS metrics export for tuning jobs, environment-based configuration, and label support for live and generate content calls.
Gemini 4 Argon: our next era of frontier intelligence
What to do: Watch for the wider release to paid API customers and plan for the announced pricing of $2 per million input tokens, $10 per million output tokens, and cached input at 95% off.
Anthropic Python SDK 1.10.0
What to do: Update to v1.10.0 to access new GA Organization API endpoints, Admin API analytics and RBAC features, and MCP tunnels beta improvements.
Show HN: Open-source model routing for coding agents at Astra-level performance
InfoReleasesHacker News · community
What to do: Try the open-source Weave Router if you want to reduce costs and latency for coding agents by routing between multiple LLMs instead of using a single frontier model.
In Python SDK 1.10.0, TypeScript SDK 0.130.0, C# SDK 12.52.0, Go SDK 1.77.0, Java SDK 2.67.0, PHP SDK 0.53.0, Ruby SDK 1.75.0, and version 1.37.0 of the ant CL…
What to do: If you use Claude Sonnet 4.5, migrate to Claude Sonnet 5.5 before the November 30, 2026 retirement, and review the migration guide for breaking changes.
We announced the deprecation of the Claude Sonnet 4.5 model (claude-sonnet-4-5-20250929), with retirement on the Claude API scheduled for November 30, 2026.
What to do: Migrate from claude-sonnet-4-5-20250929 to Claude Sonnet 5.5 before November 30, 2026.
TuesdaySeptember 29, 2026
Elevated errors across ChatGPT, Codex, and the API including the Agents API
Heads-upOpenAI
What to do: No action; resolved.
Elevated errors on claude.ai, Claude Code, Claude Cowork and the Claude API
Heads-upAnthropic
What to do: No action; resolved.