Releasesby GlyphDeprecating 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.
Also shipped Mar 24, 2026Cerebras in March 2026 →
Workers - Dynamic Workers, now in open beta
Dynamic Workers are now in open beta ↗ for all paid Workers users. You can now have a Worker spin up other Workers, called Dynamic Workers, at runtime to execute code on-demand in a secure, sandboxed environment. Dynamic Workers start in milliseconds, making them well suited for fast, secure code execution at scale.
Monitor credit usage by day
Users on credit-based plans can now see a day-by-day breakdown of their credit consumption. Head to Usage & Billing > Account usage insights > Credits to view exactly how your credits are being used each day.
Design with agents on the Figma canvas, now in beta
Through the Figma MCP server, AI agents can now write directly to your Figma files.
Multi-action CTA's for Guides & Surveys
What it is: Buttons in Guides and Surveys can now execute multiple actions in sequence rather than just one. When a user clicks, the step transition fires immediately, and additional actions (opening a URL, clicking a page element) follow in order.
- DuckDB 1.5.1 support: MotherDuck supports DuckDB 1.5.1 ("Variegata")
- DuckDB 1.5.1 support: MotherDuck supports DuckDB 1.5.1 ("Variegata"). This release brings significant performance improvements including bloom filter join pushdown, stats-only min/max evaluation, faster TopN queries with late materialization, and lazy view binding.
AI Crawl Control - Advanced WAF customization for AI Crawl Control blocks
AI Crawl Control now supports extending the underlying WAF rule with custom modifications. Any changes you make directly in the WAF custom rules editor , such as adding path-based exceptions, extra user agents, or additional expression clauses , are preserved when you update crawler actions in AI Crawl Control.
More from Cerebras InferenceEvery Cerebras Inference release →
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
Payload Optimization: msgpack and gzip /v1/chat/completions and /v1/completions now accept request bodies...
Payload Optimization: msgpack and gzip /v1/chat/completions and /v1/completions now accept request bodies encoded with msgpack (Content-Type: application/vnd.msgpack) and/or compressed with gzip (Content-Encoding: gzip). This can significantly reduce payload size and improve TTFT for requests with long prompts.
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.