Kimi K3.1 Pro and reasoning guidance
- Added Kimi K3.1 Pro to the Dedicated model catalog. Documented image inputs, images in tool results, and image-token estimates in Image Inputs. Documented Kimi K3.1 Pro reasoning levels: low, medium, high, and max (default). Updated Reasoning with model-specific effort tables and request examples, plus guidance for conversation history.
Also shipped Nov 9, 2026Cerebras in November 2026 →
AlloyDB AI smart batching and sentiment analysis are generally available
AlloyDB AI smart batching for AI functions and the ai.analyze_sentiment function are now generally available on PostgreSQL 17 and later. Smart batching improves query performance by offloading AI operations asynchronously.
BigQuery compute cost attribution is available in preview
BigQuery now supports compute cost attribution in preview, allowing users to track billed compute charges at the project level based on reservation capacity usage for FinOps reporting.
BigQuery jobs explorer performance troubleshooting is generally available
BigQuery jobs explorer now provides generally available tools for troubleshooting query performance and comparing job and system performance to diagnose regressions.
BigQuery pipeline task concurrency limits are generally available
Users can now specify the maximum number of concurrently executed tasks when creating or scheduling BigQuery pipelines.
BigQuery adds Zstandard compression functions in preview
BigQuery now supports Zstandard (Zstd) compression and decompression functions for bytes and string values in GoogleSQL, currently available in preview.
AWS Glue adds 100 new native connectors for popular SaaS applications
AWS Glue now includes 100 native connectors for SaaS and REST API applications, enabling data integration without custom code. These connectors allow teams to reuse connections across ETL jobs with existing permission models.
More from Cerebras InferenceEvery Cerebras Inference release →
Dedicated models and API guidance
- Added Kimi K3, GLM 5.3 Flash, Inkling, Reflection AI Beam, and MiMo V2.6 Pro to the Dedicated model catalog. Documented images in tool messages for enabled Gemma 4 31B, Kimi K2.7 Code, and Kimi K3 Dedicated endpoints in Image Inputs. Added Kimi K3 and GLM 5.3 Flash reasoning controls to Reasoning and OpenAI compatibility.
Clarified service-tier fallback and response behavior Updated the Service Tiers guide and Chat Completions...
Clarified service-tier fallback and response behavior Updated the Service Tiers guide and Chat Completions API reference to match the current service-tier behavior. Responses report the effective tier in service_tier. The documentation now also explains how auto can fall back to flex and how priority can retry at the request's standard priority.
Clarified service-tier fallback and response behavior
Updated the Service Tiers guide and Chat Completions API reference to match the current service-tier behavior. Responses report the effective tier in service_tier. The documentation now also explains how auto can fall back to flex and how priority can retry at the request's standard priority.
Temporary increase to Qwen 3.8 27B total token rate limit The Developer tier total token rate limit for...
Temporary increase to Qwen 3.8 27B total token rate limit The Developer tier total token rate limit for qwen-3.8-27b is temporarily increased from 450K to 750K tokens per minute (5× the uncached limit, up from the standard 3×). The uncached limit remains 150K tokens per minute. See Rate Limits for current limits.
Gemma 4 31B availability changes on public endpoints Starting September 3, 2026, gemma-4-31b is no longer...
Gemma 4 31B availability changes on public endpoints Starting September 3, 2026, gemma-4-31b is no longer available on Cerebras public endpoints. This change doesn't affect Dedicated Endpoints, where Gemma 4 31B remains available. Use qwen-3.8-27b for public endpoint workloads. To continue using Gemma 4 31B, contact us to set up a dedicated endpoint.
Qwen 3.8 27B available on public endpoints qwen-3.8-27b is now available on Cerebras public endpoints
Qwen 3.8 27B available on public endpoints qwen-3.8-27b is now available on Cerebras public endpoints. Qwen 3.8 27B is a 27-billion-parameter dense multimodal model for agentic coding, tool use, research, and long-running workflows.
Flowise integration moved to legacy status Flowise has archived its repositories and ends official support on...
Flowise integration moved to legacy status Flowise has archived its repositories and ends official support on August 31, 2026. We removed Flowise from the supported integrations directory and navigation. The legacy Flowise guide remains available for existing self-hosted deployments, but we do not recommend starting new production projects with Flowise.
GLM 4.7 reasoning_logprobs default will not ship before deprecation zai-glm-4.7 is scheduled for deprecation...
GLM 4.7 reasoning_logprobs default will not ship before deprecation zai-glm-4.7 is scheduled for deprecation on August 17, 2026 and will keep its existing default logprobs response shape until then. Requests that explicitly set the X-Cerebras-Version-Patch: 2 header still receive the separated reasoning_logprobs field.