deployedbyai

The Deploy Log | Week by week | Free, no signup

What shipped in AI, week of

53 rows are listed for in The Deploy Log, from 24 companies. Amazon Web Services shipped the most, 8 rows, then Anthropic with 7. Listed this week: Bedrock prompt caching for open-weight models, Bedrock tabular search, Nova-3 36 new languages, Qwen4 Max on OpenRouter, Tencent Hy4 flash and 48 more. Every item sourced to the publisher's own page.

In figures

FigureValue
Rows53
Rows the week before357
Change against the week before-304
Companies24
Companies seen for the first time0
Models seen for the first time0
Rows with no shipped date, placed by their edition or the day they were added0
Undated until its day2
Rows by shipped day, November 16 to 22, 2026November 16, 2026: 51 rows.51Nov 16Nov 17Nov 18Nov 19Nov 20Nov 21Nov 22
Each bar counts the rows their publishers dated that day. Not drawn: 0 rows with no shipped date, placed by an edition or by the day added; 2 rows dated ahead by the publisher, undated until that day. Data as of .

Models and APIs

Bedrock prompt caching for open-weight models

Open-weight models on Amazon Bedrock now support explicit prompt caching, with cache reads billed at a lower rate than standard input.

Amazon Web Services | Models and APIs | Published

SOURCE Amazon Web Services, Bedrock prompt caching for open-weight models

Bedrock tabular search

Amazon Bedrock Managed Knowledge Base now supports tabular search for CSV, XLSX, and XLS files.

Amazon Web Services | Models and APIs | Published

SOURCE Amazon Web Services, Bedrock tabular search

Nova-3 36 new languages

Nova-3 adds 36 monolingual languages for batch and streaming speech-to-text.

Deepgram | Models and APIs | Published

SOURCE Deepgram, Nova-3 36 new languages

Qwen4 Max on OpenRouter

Qwen4 Max is available on OpenRouter at $1.50 input and $4.50 output per 1M tokens with a 1M-token context window.

OpenRouter | Models and APIs | Published

SOURCE OpenRouter, Qwen4 Max on OpenRouter

Tencent Hy4 flash

Tencent Hy4 flash is available on OpenRouter at $0.04375 input and $0.1756 output per 1M tokens with 1M context.

OpenRouter | Models and APIs | Published

SOURCE OpenRouter, Tencent Hy4 flash

elevenlabs-python v2.79.0

Agent tools as code (tool builder) and unhandled client tool call reporting.

ElevenLabs | Models and APIs | Published

SOURCE ElevenLabs, elevenlabs-python v2.79.0

java-genai v2.4.0

Adds tool search types, static file processing options, and batch inputs for Gemini embedding models.

Google | Models and APIs | Published

SOURCE Google, java-genai v2.4.0

js-genai v3.4.0

js-genai v3.4.0 adds tool search types, static file processing options, and batch inputs with usage metadata for Gemini embedding models.

Google | Models and APIs | Published

SOURCE Google, js-genai v3.4.0

python-genai v3.4.0

python-genai v3.4.0 released with tool search types, batch inputs for Gemini embeddings, and bug fixes.

Google | Models and APIs | Published

SOURCE Google, python-genai v3.4.0

Tools and products

Pydantic AI v2.69.0

Pydantic AI v2.69.0 adds Gemini 4 Hydrogen support on GoogleModel and GroqModel service_tier support.

Pydantic | Tools and products

SOURCE Pydantic, Pydantic AI v2.69.0

Z-Image-Turbo on Amazon ECS

AWS Professional Services released a deployable solution running Z-Image-Turbo on AWS Inferentia2 via Amazon ECS, with 512px images at $0.003 and 1024px at $0.011.

Amazon Web Services | Tools and products

SOURCE Amazon Web Services, Z-Image-Turbo on Amazon ECS

AI Gateway Private Inference

Private Inference connects your own model endpoints to AI Gateway with the same authentication, SDKs, APIs, and observability as catalog models.

Vercel | Tools and products | Published

SOURCE Vercel, AI Gateway Private Inference

AWS DevOps Agent

AWS DevOps Agent is now available in AWS GovCloud (US-West).

Amazon Web Services | Tools and products | Published

SOURCE Amazon Web Services, AWS DevOps Agent

AgentCore runtime instances

AgentCore runtime instances are now available in six additional AWS Regions: US West (N. California), Canada (Central), Europe (London), Europe (Paris), Europe (Stockholm), and Asia Pacific (Seoul).

Amazon Web Services | Tools and products | Published

SOURCE Amazon Web Services, AgentCore runtime instances

Amazon S3 Vectors hybrid search

Hybrid search combining vector similarity and full-text search in a single QueryVectors call, available today in all commercial AWS Regions.

Amazon Web Services | Tools and products | Published

SOURCE Amazon Web Services, Amazon S3 Vectors hybrid search

Amazon WorkSpaces for AI agents

New capabilities let users set up, connect, and govern AI agents faster.

Amazon Web Services | Tools and products | Published

SOURCE Amazon Web Services, Amazon WorkSpaces for AI agents

Anthropic Go SDK v2.10.0

Adds source and error codes to RBAC Role read endpoints, Update Bundle API, and owner-only agent toolset files.

Anthropic | Tools and products | Published

SOURCE Anthropic, Anthropic Go SDK v2.10.0

Anthropic Java SDK v3.9.0

Adds source and error codes to RBAC Role read endpoints, Update Bundle API, and Vertex default credential scope.

Anthropic | Tools and products | Published

SOURCE Anthropic, Anthropic Java SDK v3.9.0

Anthropic TypeScript SDK v1.9.0

Adds source and error codes to RBAC Role read endpoints, Update Bundle API, and streaming tool input validation.

Anthropic | Tools and products | Published

SOURCE Anthropic, Anthropic TypeScript SDK v1.9.0

Show the other 31 rows

MLX-VLM v0.8.0

MLX-VLM v0.8.0 adds QAT training, distributed streaming and cluster management, and support for MiniMax-H3-Image, Ling 3.1 Flash, Ripple-65B-Preview, DFlash2, DeepSeek V4.1 DSpark, ERNIE 5.5 Flash Base, and Inkling 2.

MLX-VLM | Tools and products | Published

SOURCE MLX-VLM, MLX-VLM v0.8.0

Robotics, hardware and chips

CUDA-X libraries for scientific discovery

New CUDA-X libraries cuPhoton, cuPotential and cuSpa are available, with cuPhoton.xBeam cutting black hole correlation from over a month to eight minutes.

NVIDIA | Robotics, hardware and chips | Published

SOURCE NVIDIA, CUDA-X libraries for scientific discovery

NVIDIA Vera CPU platform

The Vera CPU rack-scale platform combines 192 Vera CPUs with Quantum-X800 InfiniBand, delivering over 200TB/s aggregate peak memory bandwidth.

NVIDIA | Robotics, hardware and chips | Published

SOURCE NVIDIA, NVIDIA Vera CPU platform

Nemotron for Science

Nemotron for Science brings Nemotron 3.5 Super VL, LitmusBench v0.2 with nearly 50,000 chemistry questions, and post-training recipes for science agents.

NVIDIA | Robotics, hardware and chips | Published

SOURCE NVIDIA, Nemotron for Science

One line every time AI actually ships, around the clock, free on Threads and Bluesky. Every one is in The Deploy Log with its source.

The Saturday edition is the week in one, free to read on the site, and by email if you want it: get it by email.