Releasesby GlyphStreaming: 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.
Also shipped Mar 30, 2026Cerebras in March 2026 →
AI Image Tools now in FigJam, Slides, & Buzz
AI image tools like Expand, Erase, and Isolate are now in FigJam, Slides, and Buzz (beta), with Vectorize available in Slides and Buzz.
Updated visualization suggestions now generally available
In January 2026, we announced improvements to visualization suggestions in public preview. These changes included higher quality suggestions leveraging information provided by data sources, as well as minor user interface updates. These improvements are now generally available.
Edit guide and survey positions without leaving Preview mode
What it is: The Guide Preview now includes an Edit button. Click it to adjust form factor options like position and layout, then save to see changes reflected in both the Preview and the Dashboard right away.
Modal 1.4.1
- We're introducing a concept of "readiness probes" for modal.Sandbox. This feature lets you configure a readiness check on a TCP port (modal.Probe.with_tcp()) or by executing a process (modal.Probe.with_exec()).
WAF Release - 2026-03-30
This week's release introduces new detections for a critical authentication bypass vulnerability in Fortinet products (CVE-2025-59718), alongside three new generic detection rules designed to identify and block HTTP Parameter Pollution attempts.
More from Cerebras InferenceEvery Cerebras Inference release →
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
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.
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.
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.
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.
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.
New parameter: prompt_cache_key /v1/chat/completions and /v1/completions now accept an optional...
New parameter: prompt_cache_key /v1/chat/completions and /v1/completions now accept an optional prompt_cache_key parameter. Requests that share the same key are routed together so they reuse the same prompt cache, increasing cache hits and reducing time to first token.