Releasesby GlyphAdded support for parallel tool calling, allowing models to request multiple tool invocations simultaneously...
Added support for parallel tool calling, allowing models to request multiple tool invocations simultaneously in a single response. This reduces latency when handling queries that require multiple independent operations. Learn more in our Tool Calling guide.
Also shipped Dec 17, 2025Cerebras in December 2025 →
Gemini 3 Flash Preview now available in AI Gateway
Google’s Gemini 3 Flash Preview is now available through AI Gateway. You can call this model from Netlify Functions without configuring API keys; the AI Gateway provides the connection to Google for you.
Forms - Flows Auth0 Send Email Action
We’re excited to announce that we added __Flows Auth0 Send Email Action__! This new feature allows you to send emails from Flows using the customized Email Provider at your Auth0 Tenant.
Discount Function support for rejecting discount codes
The Discount Function API now supports discount code rejection, allowing apps to conditionally reject discount codes with a custom message. With discount rejection for the Discount Function API, merchants can: Prevent double discounting on sale prices Manage fine-grained combinations of discount codes Disqualify certain products from discounts For more...
- MotherDuck MCP Server: Your favorite AI assistant can now talk directly to your data
- MotherDuck MCP Server: Your favorite AI assistant can now talk directly to your data. Connect Claude, ChatGPT, Cursor, or any MCP-compatible client to MotherDuck using the MotherDuck remote MCP Server at https://api.motherduck.com/mcp .
Prisma ORM 7.2.0 Released: CLI Improvements, Bug Fixes & Better Configs
Prisma ORM 7.2.0 includes CLI improvements such as the return of the --url flag, smarter initialization configurations for Node and Bun, and various bug fixes.
Gateway, Cloudflare One - Shadow IT - domain level SaaS analytics
Zero Trust has again upgraded its Shadow IT analytics , providing you with unprecedented visibility into your organizations use of SaaS tools. With this dashboard, you can review who is using an application and volumes of data transfer to the application.
More from Cerebras InferenceEvery Cerebras Inference release →
Process large-scale inference workloads asynchronously with the new Batch API and Files API
Process large-scale inference workloads asynchronously with the new Batch API and Files API. Submit up to 50,000 requests in a single batch job and get 50% cost savings. Learn more in our Batch guide.
Streaming Support Streaming is now supported for all models, including with structured output requests...
Streaming Support Streaming is now supported for all models, including with structured output requests (response_format, tools). Reasoning Format Controls Added reasoning_format parameter for reasoning models, giving you control over how reasoning text appears in responses.
Added support for prompt caching, which automatically stores and reuses prompt prefixes to reduce latency and...
Added support for prompt caching, which automatically stores and reuses prompt prefixes to reduce latency and improve time to first token for similar requests. Learn more in our Prompt Caching guide.
Constrained Decoding Generally Available Constrained decoding has moved to General Availability (GA) with...
Constrained Decoding Generally Available Constrained decoding has moved to General Availability (GA) with expanded capabilities. Supported models Structured Outputs and Tool Calling with strict: true are now available on the following models: gpt-oss-120b llama-3.1-8b qwen-3-235b-a22b-instruct-2507 qwen-3-32b zai-glm-4.6 zai-glm-4.7 New capabilities...
We now support Predicted Outputs for faster generation when large portions of the output are known in advance
We now support Predicted Outputs for faster generation when large portions of the output are known in advance. Provide a draft of the expected response via the prediction field, and the model will efficiently reuse unchanged tokens while regenerating only those that differ. Ideal for code editing, document revisions, and template-based responses.
Prioritize requests to the API to balance latency sensitivity and resource allocation across your workloads...
Prioritize requests to the API to balance latency sensitivity and resource allocation across your workloads with the new Service Tiers feature. Learn more in our Service Tiers guide.