Releasesby GlyphRolling 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.
Also shipped Mar 27, 2026Cerebras in March 2026 →
Deploy from Codex with the Netlify Plugin
You can now deploy sites to Netlify directly from OpenAI Codex using the Netlify plugin in the Codex plugin directory. Netlify plugin in Codex Codex plugins extend Codex with apps, skills, and MCP servers, to access external tools, data, and workflows directly from your coding environment.
Qdrant 1.17.1
Change log Improvements milestone#46 - Defer point updates, efficiently apply and optimize points with prevent_unoptimized=true #8188 - Make Gridstore flushes non-blocking to reduce search tail latencies #8235 - Improve performance of filtered search in case of singular payload value #8402 - Add request tracing ID into audit log #8460 - Propagate WAL errors...
Cache prewarm, Stripe Projects integration, Neon Auth webhooks with Resend, and more release - Mar 27, 2026
Neon Postgres in Stripe Projects. Neon is now part of Stripe Projects. Stripe Projects is a Stripe CLI workflow for hooking an app up to backends. You pick serv...
What's new in Sigma
Admin Support for Azure customer-owned cloud storage integration Admins can now add an Azure Blob Storage integration to use customer-owned cloud storage with the following features: CSV upload File upload column in input tables Export to cloud storage This adds Azure to the existing AWS and GCP storage options that give your organization control over where...
Workers - New RFC 9440 mTLS certificate fields in Workers
Four new fields are now available on request.cf.tlsClientAuth in Workers for requests that include a mutual TLS (mTLS) client certificate. These fields encode the client certificate and its intermediate chain in RFC 9440 ↗ format , the same standard format used by the Client-Cert and Client-Cert-Chain HTTP headers , so your Worker can forward them directly...
One-click CDN, Railway x Stripe Projects, HA Postgres
Your users in Tokyo shouldn't wait for bytes to travel from us-west. Starting this week, they don't have to. We're shipping a built-in CDN you can enable in one click, a partnership with Stripe that lets agents provision Railway in one command, and a one-click path to high-availability Postgres for everyone. Let's get into it!
More from Cerebras InferenceEvery Cerebras Inference release →
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.
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.
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.
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.
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.