The radar watched 63 sources across 32 tools this window and published 28 changes; these are the twelve worth your attention, ranked. That's two more than the typical ten: three separate tools, Langfuse, the Vercel AI SDK, and Weaviate, removed legacy APIs in the same week, and Neon's backend GA landed alongside the pricing change that ends its free beta, so both halves of that story stayed in rather than cutting one.

Neon — Neon backend reaches general availability (GA)

Neon's backend is now generally available, expanding from serverless Postgres into a full backend platform where every branch is a complete copy of the stack, not just the database. Object Storage, Functions, and AI Gateway move out of free beta at the same time (see the pricing change below), so budget for them before scaling up.

Neon — Object Storage, Functions, and AI Gateway billing activated; previously free during beta

Following the GA above, Neon starts charging for Object Storage ($0.023 per GB-month), Functions (compute and invocations), and AI Gateway (prepaid credits at provider list price, no markup). Anyone who built on these during the free beta needs to re-check their bill.

Pinecone — Gemini 2.5 Pro and o4-mini models deprecated; automatic routing to newer models implemented

Google deprecated Gemini 2.5 Pro and OpenAI deprecated o4-mini; Pinecone Assistant now silently routes any request naming those models to Gemini 3.5 Flash or GPT-5 instead, at the same price. Convenient, but it also means your Assistant calls may already be running on a different model than the one in your code.

Vercel AI SDK — @ai-sdk/[email protected] removes Chat Completions API

@ai-sdk/xai 5.0.0 drops the Chat Completions API entirely, keeping only the newer Responses-style interface. If you're on an older xai integration, this upgrade breaks it rather than just deprecating it.

Langfuse — API now rejects legacy GET reads for new organizations

Langfuse now rejects legacy GET-based reads for any newly created organization; existing orgs keep the old behavior for now. New projects should build against the current read API from day one rather than copying patterns from an older integration.

Weaviate — Removal of /v1/modules endpoint and contextionary extension/concept handlers

Weaviate removed the /v1/modules REST endpoint along with the contextionary extension and concept handlers. If any tooling still queries /v1/modules or relies on contextionary concept expansion, it stops working on upgrade, not just prints a deprecation warning.

GLM API — Introduction of GLM-5.3-FlashX model with tiered pricing structure

Z.ai introduced GLM-5.3-FlashX at $0.37 and $0.075 per million tokens, with a limited-time free tier and $1.25 batch pricing. Check the pricing page directly for which rate applies to input versus output before committing a workload to it.

DeepSeek API — DeepSeek-Flash pricing structure introduced with off-peak and peak rates

DeepSeek-Flash now bills separately for off-peak and peak hours: cache-hit input runs $0.003 off-peak versus $0.006 peak, cache-miss input $0.15 versus $0.3, output $0.6 versus $1.2 per million tokens. Workloads that can shift to off-peak hours get roughly half price.

Kimi API — Introduced K3 Series Models with context cache pricing structure

Kimi's new K3 series models introduce two cache TTL tiers, 5 minutes and 1 hour (5 minutes is the default when unspecified). Cache writes are billed separately per tier, but a cache hit is billed only at the cached-input rate with no extra write charge, and each hit refreshes the entry's lifetime.

OpenAI API — Added API key governance controls at organization and project levels

OpenAI added API key creation governance at the organization and project level: admins can restrict new keys to service accounts only, to user-owned project keys only, or block new key creation entirely. Existing keys keep working, and org-level restrictions override project settings.

Claude Code — Added AGENTS.md support as alternative to CLAUDE.md for project instructions

Claude Code now reads AGENTS.md instead of CLAUDE.md when a project has no CLAUDE.md, toggled under Project instructions in /config. Useful if you already maintain an AGENTS.md for other agent tools and don't want to duplicate it, though it's not yet available on Bedrock, Vertex, or Foundry.

GitHub Copilot — Copilot budget increase requests workflow now generally available

GitHub Copilot's budget increase request flow is now generally available: when a member hits their AI credit limit, they can request more instead of just getting blocked, and org or enterprise owners approve, adjust, or deny the request from settings. Worth turning on before your team's heaviest Copilot users start hitting the wall silently.

Read on the web: https://devtoolsradar.com/weekly/2026-09-20-issue-10/ (中文版: https://devtoolsradar.com/zh/weekly/2026-09-20-issue-10/)