Releasesby GlyphPayload 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.
Also shipped Apr 10, 2026Cerebras in April 2026 →
What's new in Sigma
AI apps Input table audit history (Beta) Input table audit history records versioned snapshots of input table row and schema changes over time. For each input table, Sigma automatically creates a warehouse-native view in your data platform that can help you understand the following: Row-level history: What changed in a specific row, who made the change, and...
New discount fields in the Storefront API's cart types
As of API version 2026-07, several changes have been introduced to the discount fields and amounts in the Storefront API . What's changed Deprecated Fields : The cart.discountAllocations field is deprecated. Use cart.lines[].discountAllocations(lineLevelOnly: false) and cart.deliveryGroups[].discountAllocations instead.
Web Experiment: Mobile Simulator
Description: The web experiment visual editor now supports simulating various device sizes directly within the overlay. Choose from popular device presets or specify a custom width/height, enabling users to preview edits to their site in all viewports. All existing visual editor features are supported in mobile mode.
Neon Auth Plugins tab, Neon Skill for coding agents, Sentry and Neon MCP guide release - Apr 10, 2026
Plugins tab for Neon Auth Organization settings. The Neon Auth page now includes a Plugins tab. Organization plugin settings (limits, creator role, invitation e...
Browser Isolation - Canvas Remoting optimizes performance for productivity applications
Remote Browser Isolation now supports Canvas Remoting , improving performance for HTML5 Canvas applications by sending vector draw commands instead of rasterized bitmaps.
Browser Run - Browser Rendering adds Chrome DevTools Protocol (CDP) and MCP client support
Browser Rendering now exposes the Chrome DevTools Protocol (CDP) , the low-level protocol that powers browser automation. The growing ecosystem of CDP-based agent tools, along with existing CDP automation scripts, can now use Browser Rendering directly.
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
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 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.
Validation Errors Now Return 400 Instead of 422 API requests that fail validation now return HTTP 400 Bad...
Validation Errors Now Return 400 Instead of 422 API requests that fail validation now return HTTP 400 Bad Request instead of 422 Unprocessable Entity, aligning the HTTP status code with standard behavior across major inference providers.
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.