Releasesby GlyphAPI Version 2 Available for Testing API version 2 is now available for testing via the...
API Version 2 Available for Testing API version 2 is now available for testing via the X-Cerebras-Version-Patch header. This version introduces stricter validation and breaking changes.
Also shipped Jan 21, 2026Cerebras in January 2026 →
Introducing: Postgres Best Practices
Supabase has released Agent Skills for Postgres Best Practices to assist AI coding agents in generating high-quality, correct Postgres code.
Prisma ORM 7.3.0: Faster Query Compilation, Safer BigInt JSON, Better Adapters
Prisma ORM 7.3.0 introduces a new compilerBuild option, speeds up raw queries, and improves stability for MSSQL and better-sqlite3.
Nova-3 Model Update
🌐 Nova-3 supports 12 new languages We're pleased to announce the addition of 12 new languages for Nova-3 monolingual models. This expansion makes Nova-3 even more versatile and accessible for global users.
India DERP Region City Name updated
- Changed: The city name for the DERP server hosted in India has been updated to reflect the official name of Bengaluru. The hosting provider and IP addresses remain unchanged.
Legacy Management of Connection's Enabled Clients
The `enabled_clients` field, within the connection object, is deprecated in the following scenarios: * [Retrieving multiple connections](https://auth0.com/docs/api/management/v2/connections/get-connections) using (GET - `/api/v2/connections`).
Storefront API now returns a specific error code when Cart Transform Functions fail
As of API version 2026-04, the Storefront API will return a MERCHANDISE_LINE_TRANSFORMERS_RUN_ERROR cart error code when a Cart Transform Function encounters a runtime error during cart operations such as cartCreate or cartLinesAdd .
More from Cerebras InferenceEvery Cerebras Inference release →
Monitor your dedicated inference endpoints with the new Metrics API, providing Prometheus-compatible metrics...
Monitor your dedicated inference endpoints with the new Metrics API, providing Prometheus-compatible metrics for requests, tokens, latency percentiles, and endpoint health. Metrics are aggregated at the minute level and integrate directly with Prometheus. Learn more in our Metrics guide.
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.
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...
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 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.
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.
reasoning_effort="none" support for GLM 4.7 zai-glm-4.7 now accepts the reasoning_effort parameter
reasoning_effort="none" support for GLM 4.7 zai-glm-4.7 now accepts the reasoning_effort parameter. Reasoning is enabled by default , set reasoning_effort="none" to disable it for simple tasks where verbose reasoning blocks are unnecessary. The disable_reasoning parameter continues to be supported but will be deprecated soon.