Releasesby GlyphLogprob 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.
Also shipped Mar 25, 2026Cerebras in March 2026 →
Modal 1.4.0
We've made significant CLI enhancements so that Modal logs can be more accessible to coding agents: The modal app logs and modal container logs commands now have the ability to fetch historical logs using counting (e.g. --tail 1000) or time-based (e.g., --since 4h, --until 2026-03-15, etc.) configuration.
Attribution Alerts
Set alerts scoped to specific teams, services, environments, and more using cost attribution labels We’re excited to announce the general availability of Attribution Alerts in the Cost Management and Billing app!
The Shopify CLI app release `--force` flag is deprecated and will be removed
We are deprecating the --force flag on the shopify app deploy and shopify app release commands. The flag will be removed in a Shopify CLI release in May 2026. Why we're making this change The --force flag skips all confirmation prompts, including for extension deletions that can permanently remove data on installed shops.
New Filters for List Session Replays
What it is: Two new filters are now available on the List Session Replays API endpoint. 'amplitude_id' (integer) returns replays tied to a specific Amplitude user ID. 'replay_id' accepts up to 100 IDs in 'device_id/session_id' format and fetches those sessions directly, bypassing pagination.
Improvements to Distributions
What it is: Frequency charts, histogram charts, session length, and time-to-convert now support normalization, PDF, and CDF views. Normalization scales each series so its bars sum to 1, making groups with different sample sizes directly comparable , for example, U.S.
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.
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.
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.