Releasesby Glyphreasoning_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.
Also shipped Feb 27, 2026Cerebras in February 2026 →
Dataflow support for the C4A machine series of Arm processors is now generally available
Dataflow support for the C4A machine series of Arm processors is now generally available. Arm-based VMs are optimized for power efficiency and can provide improved price-performance for many workloads. For more information, see Use Arm VMs on Dataflow .
What's new in Sigma
AI apps Call API action (Beta) You can create actions that call API endpoints in Sigma workbooks. This allows you to trigger workflows, enrich data, and interact with external systems without leaving Sigma. See Create actions that call API endpoints .
Access - Export MCP server portal logs with Logpush
Availability Only available on Enterprise plans. MCP server portals now supports Logpush integration. You can automatically export MCP server portal activity logs to third-party storage destinations or security information and event management (SIEM) tools for analysis and auditing.
Gateway - New protocols added for Gateway Protocol Detection (Beta)
Gateway Protocol Detection now supports seven additional protocols in beta: Protocol Notes IMAP Internet Message Access Protocol , email retrieval POP3 Post Office Protocol v3 , email retrieval SMTP Simple Mail Transfer Protocol , email sending MYSQL MySQL database wire protocol RSYNC-DAEMON rsync daemon protocol LDAP Lightweight Directory Access Protocol...
- Write support for the MCP server is now live: Users can now perform write operations via the MCP Server...
- Write support for the MCP server is now live: Users can now perform write operations via the MCP Server using the new query_rw tool. This enables programmatic data modification workflows in addition to read queries. Refer to the documentation and setup guide for read-only access for more details.
More from Cerebras InferenceEvery Cerebras Inference release →
Deprecating disable_reasoning parameter for zai-glm-4.7 The disable_reasoning parameter is deprecated and...
Deprecating disable_reasoning parameter for zai-glm-4.7 The disable_reasoning parameter is deprecated and will no longer be supported after July 21, 2026. Migrate to reasoning_effort="none" to disable reasoning on zai-glm-4.7. See the Reasoning guide and Chat Completions API reference for details.
Logprob Consistency Logprobs are now computed from the model's raw output, before applying temperature scaling
Logprob Consistency Logprobs are now computed from the model's raw output, before applying temperature scaling. Previously, logprob values would vary with temperature , they now remain consistent regardless of the temperature used. This aligns with standard behavior across major inference providers and vLLM. Sampled outputs are unaffected.
Temperature Parameter: Increased Maximum The maximum allowed value for the temperature parameter for Chat...
Temperature Parameter: Increased Maximum The maximum allowed value for the temperature parameter for Chat Completions has been increased from 1.5 to 2.0. This aligns with the range supported by OpenAI, Fireworks, and other major LLM providers. Higher temperature values produce more random and creative outputs.
developer Message Role (gpt-oss-120b) The Chat Completions API now supports the developer message role for...
developer Message Role (gpt-oss-120b) The Chat Completions API now supports the developer message role for gpt-oss-120b, aligning with the OpenAI API message format. The developer role is functionally equivalent to system , the system role remains supported for backwards compatibility. Other models do not support the developer role.
Rolling out selective 4-bit weight-only quantization for supported models, targeting non-sensitive layers...
Rolling out selective 4-bit weight-only quantization for supported models, targeting non-sensitive layers while preserving full precision for sensitive layers, in line with industry standards. Learn more in Supported Models.
Streaming: Server-Sent Events (SSE) Streaming responses for Chat Completions (/v1/chat/completions) and...
Streaming: Server-Sent Events (SSE) Streaming responses for Chat Completions (/v1/chat/completions) and Completions (/v1/completions) now emit a standard data: [DONE] SSE event at the end of the stream, following the SSE standard (see the living specification). The [DONE] marker is guaranteed to appear exactly once and is always the last event in the stream.
New Sampling Parameters The following parameters are now available on all models: - frequency_penalty –...
New Sampling Parameters The following parameters are now available on all models: frequency_penalty – Reduces repetition by penalizing tokens based on how often they have appeared so far presence_penalty – Reduces repetition by penalizing tokens that have appeared at least once logit_bias – Adjusts the likelihood of specific tokens appearing in the response
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.