We've launched Claude Haiku 5.5 (claude-haiku-5-5), our most capable model tuned for high-volume and latency-sensitive work.
What to do: Review the migration guide before switching existing Claude Haiku 4.5 integrations to Claude Haiku 5.5.
AIWire: AI model shutdowns, prices and API changes
The wire
Every change we detect, newest first. Times are Eastern (ET). Archive
WednesdayOctober 7, 2026
We've lowered the price of prompt cache reads on Claude Sonnet 5.5 from $0.20 USD to $0.10 USD per million tokens: 0.05x the base input price instead of 0.1x.
What to do: Review your prompt caching costs on Claude Sonnet 5.5 to capture the reduced read price; no code changes are needed.
Anthropic Python SDK 1.12.0
What to do: Update the Python SDK to v1.12.0 to pick up the new API fields and fixes.
riva-translate-4b-instruct-v1.1 no longer appears on NVIDIA's model catalog
What to do: Check the model still answers; it is no longer on NVIDIA's model list.
TuesdayOctober 6, 2026
Google removed the shutdown date for gemini-3.1-flash-image
What to do: No action; the shutdown date was withdrawn.
Elevated errors loading usage data on platform.claude.com
Heads-upAnthropic
What to do: No action; resolved.
OpenAI Python SDK 3.26.0
What to do: Update the OpenAI Python SDK to v3.26.0 if you want to use the new Decisions feature.
Google deprecated gemini-omni-flash-preview: shuts down no earlier than Oct 22, 2026 (move to gemini-omni-1.1-flash)
What to do: Move to gemini-omni-1.1-flash before Oct 22, 2026.
Google moved the shutdown date for gemini-2.5-flash-image from no earlier than Oct 2, 2026 to no earlier than Mar 15, 2027
What to do: Move to gemini-3.1-flash-lite-image before Mar 15, 2027.
Google deprecated gemini-3.1-flash-image: shuts down no earlier than Oct 29, 2026 (move to gemini-nano-banana-2.1)
What to do: Move to gemini-nano-banana-2.1 before Oct 29, 2026.
Google deprecated gemini-2.5-pro-preview-tts: shuts down no earlier than Nov 17, 2026 (move to gemini-3.8-flash-tts)
What to do: Move to gemini-3.8-flash-tts before Nov 17, 2026.
Google deprecated gemini-2.5-flash-preview-tts: shuts down no earlier than Nov 17, 2026 (move to gemini-3.8-flash-tts)
What to do: Move to gemini-3.8-flash-tts before Nov 17, 2026.
Google deprecated gemini-2.5-flash-native-audio-preview-12-2025: shuts down no earlier than Nov 17, 2026 (move to gemini-3.8-live)
What to do: Move to gemini-3.8-live before Nov 17, 2026.
Google deprecated gemini-3.1-flash-live-preview: shuts down no earlier than Nov 17, 2026 (move to gemini-3.8-live)
What to do: Move to gemini-3.8-live before Nov 17, 2026.
Google deprecated gemini-3.1-flash-tts-preview: shuts down no earlier than Nov 17, 2026 (move to gemini-3.8-flash-tts)
What to do: Move to gemini-3.8-flash-tts before Nov 17, 2026.
Gemini Nano Banana 2.1 generally available (GA) : Released Gemini Nano Banana 2.1 (gemini-nano-banana-2.1), the latest high-efficiency image generation and con…
What to do: Migrate image generation code from gemini-3.1-flash-image to gemini-nano-banana-2.1 before the October 29, 2026 shutdown.
Released the Decisions API in beta with gpt-6-luna.
What to do: Try the beta Decisions API at v1/decisions with gpt-6-luna if you need faster typed answers from text or images.
Simplified API usage tiers from five to three: Build, Launch, and Grow.
What to do: Review the usage tiers documentation to see the new monthly limits and rate limits for your organization's tier.
OpenAI Python SDK 3.25.0
What to do: Update the OpenAI Python SDK to v3.25.0 to pick up the new agents and tool features.
Mistral Python SDK 3.1.0
What to do: Upgrade to the Mistral Python SDK v3.1.0 on PyPI and update code that uses the removed Runs/Records methods or changed authentication and pipeline types.
Introducing Mistral Large 4
What to do: Try the Mistral Large 4 preview API in Mistral Studio and plan for open-weight availability by end of the month.
We've added capabilities.server_tools to the Models API.
What to do: Read capabilities.server_tools from the Models API endpoints to check tool support per model instead of hardcoding it.
MondayOctober 5, 2026
Added an in-product flow for HIPAA compliance support in API Organization settings > General.
What to do: If your organization needs HIPAA compliance, have an admin enable it in API Organization settings > General and review the Help Center eligibility and configuration requirements.
xAI deprecated grok-imagine-image-quality: shuts down Nov 2, 2026
What to do: Plan a move before Nov 2, 2026.
Elevated errors for Claude Mythos 5.1 and Claude Fable 5.1
Heads-upAnthropic
What to do: No action; resolved.