gpt-4.1-nano has been retired
What to do: Requests to gpt-4.1-nano now fail. Switch to gpt-5.6-luna.
Every change we detect, newest first. Times are Eastern (ET). Archive
What to do: Requests to gpt-4.1-nano now fail. Switch to gpt-5.6-luna.
What to do: Requests to gpt-4-turbo now fail. Switch to gpt-5.6-sol.
What to do: Requests to gpt-4-1106-preview now fail. Switch to gpt-5.6-sol.
What to do: Requests to gpt-4-0613 now fail. Switch to gpt-5.6-sol.
What to do: Requests to gpt-3.5-turbo-0125 now fail. Switch to gpt-5.6-terra.
What to do: Check the model still answers; it is no longer on NVIDIA's model list.
What to do: Update the google-genai Python SDK to 2.33.0 if you need the new config options or retry fixes.
What to do: Call it as nemotron-3.5-bolt-e4b.
What to do: If you use Google Cloud, consider accessing the Claude API through your Google Cloud project and configure IAM access and Marketplace billing.
What to do: Update type handling in code using Decisions: check isinstance(question.instructions, str) before string operations and revise exhaustive type checks for the new input types.
What to do: Review the Decisions API to see if it fits low-latency, low-cost decision workloads in your app.
What to do: Review the changes since public beta and update your Decisions API integrations to use the new features and 400-question limit.
What to do: Review the reference implementation and Google Cloud documentation if you're building autonomous remediation agents on Gemini platform or ADK.
What to do: Try streaming by creating a new gateway with the opt-in Preview flag pointed at an existing SSE backend, and implement client reconnection logic for streams that may end before the one-hour limit.
What to do: Try installing the CLI via Homebrew or Go, and if you use image variations, switch to images edit with a GPT Image model.
What to do: No action; resolved.
What to do: Update the Anthropic Python SDK to 2.1.0 if you need the new user profile enforcement features.
What to do: Review the migration guide and SDK/CLI breaking changes before upgrading to the new major SDK versions and API version 2026-10-21.
What to do: If you want self-hosted durable agents with your own models, try Omnara via its GitHub repo or hosted version.
What to do: Upgrade to openai 3.36.0 if you need Vertex AI Responses API support, cache-write usage counts, or the WebSocket and validation fixes.
What to do: Upgrade to the 2.0.0 Python SDK and review the breaking changes, including the new 2026-10-21 API version, before updating your integration.
What to do: If you build with open-weight coding models, evaluate generated code under your real customer and topic personas and add human review of authentication and access-control code before production.
What to do: Watch for availability in Gemini's Model Garden if you want to access OpenAI models through Google Cloud Marketplace.
What to do: Consider running attack surface analysis (e.g. the published Claude skill or the described three-pass methodology) over your own codebases to find unnecessarily reachable code and risky configuration…
What to do: Update to google-genai 2.32.0 to pick up the new Live API context-update support and response-parsing fixes.
What to do: Call it as nemotron-3.5-rerank-8b.
What to do: Call it as nemotron-3.5-embed-8b.