Releasesby GlyphStreaming 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.
Also shipped Dec 16, 2025Cerebras in December 2025 →
Own Your Observability: Supabase Metrics API
The Metrics API allows users to stream database telemetry into Prometheus-compatible observability stacks for monitoring and alerting.
AI Gateway now Generally Available
AI Gateway is now generally available (GA) for all Netlify users. Build AI-powered apps with confidence using our fully managed gateway that handles AI model keys, setup, and monitoring automatically. For a deeper dive into AI Gateway capabilities, check out our latest blog post.
New Prerender extension
The Prerender extension is now generally available (GA) for all Netlify users. The legacy prerendering feature is now deprecated with limited support. Once set up, this extension automatically serves pre-rendered HTML to crawlers, agents, and preview services, while regular site visitors continue to receive your standard JavaScript application.
Release of Mistral Small Creative
Mistral Small Creative (labs-mistral-small-creative) has been released as a Labs model.
- DuckDB 1.4.3: MotherDuck supports DuckDB 1.4.3, a bugfix release
- DuckDB 1.4.3: MotherDuck supports DuckDB 1.4.3, a bugfix release. Learn more in the official DuckDB Labs 1.4.3 announcement and changelog . PlanetScale Postgres integration: Users of PlanetScale Postgres can now use pg_duckdb to push analytical queries to MotherDuck.
Modal 1.2.6
- Fixed bug where iterating on a modal.Sandbox.exec output stream could raise unauthenticated errors.
More from Cerebras InferenceEvery Cerebras Inference release →
Added 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.
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.
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.
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.
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...
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.