Releasesby GlyphDeprecated llama-4-scout-17b-16e-instruct See Deprecations for more details
Deprecated llama-4-scout-17b-16e-instruct See Deprecations for more details.
Also shipped Nov 3, 2025Cerebras in November 2025 →
Workflows are now in Alpha and I already broke mine
PostHog introduced Workflows in alpha, an automation builder that triggers actions based on live user behavior and event data.
2.32.0 (2025-10-28)
Features Adds Python 3.14 support ( #1512 ) ( 95a2690 ) Debug logs ( #1460 ) ( b5d4a45 ) Support the protocol version in StreamingPullRequest ( #1455 ) ( e6294a1 ) Bug Fixes Ignore future warnings on python versions ( #1546 ) ( 8e28dea )
2.33.0 (2025-10-30)
Features Add AwsKinesisFailureReason.ApiViolationReason ( ac68093 ) Add tags to Subscription, Topic, and CreateSnapshotRequest messages for use in CreateSubscription, CreateTopic, and CreateSnapshot requests respectively ( ac68093 ) Annotate some resource fields with their corresponding API types ( ac68093 ) Bug Fixes Deprecate credentials_file argument (...
Deployment setup monitoring
Enterprise customers can now get notified when deployments fail to start and customize how long to wait before timing out.
WAF Release - 2025-11-03
This week highlights enhancements to detection signatures improving coverage for vulnerabilities in Adobe Commerce and Magento Open Source, linked to CVE-2025-54236. Key Findings This vulnerability allows unauthenticated attackers to take over customer accounts through the Commerce REST API and, in certain configurations, may lead to remote code execution.
Workers - Capture Wrangler command output in structured format
You can now capture Wrangler command output in a structured ND-JSON ↗ format by setting the WRANGLER_OUTPUT_FILE_PATH or WRANGLER_OUTPUT_FILE_DIRECTORY environment variables.
More from Cerebras InferenceEvery Cerebras Inference release →
Deprecated qwen-3-coder-480b
Deprecated qwen-3-coder-480b. We recommend migrating to Z.ai GLM 4.7.
Added support for retrieving log probabilities via the logprobs parameter for the Completions endpoint
Added support for retrieving log probabilities via the logprobs parameter for the Completions endpoint. Set to an integer (0-20) to return the most likely alternative tokens at each position, or null to disable.
We now support Predicted Outputs for faster generation when large portions of the output are known in advance
We now support Predicted Outputs for faster generation when large portions of the output are known in advance. Provide a draft of the expected response via the prediction field, and the model will efficiently reuse unchanged tokens while regenerating only those that differ. Ideal for code editing, document revisions, and template-based responses.
We're gradually introducing multi-token streaming across our models
We're gradually introducing multi-token streaming across our models. Instead of sending tokens individually, we'll now deliver them in batches through 200 evenly-spaced events per second. This change eliminates the artificial delays that occurred with single-token streaming.
Updated support for OpenAI GPT-OSS (gpt-oss-120b) - Tool calling with strict: true (constrained decoding) -...
Updated support for OpenAI GPT-OSS (gpt-oss-120b) Tool calling with strict: true (constrained decoding) Response format with json_schema when using strict=true Response format with json_object when using strict=true tool_choice: none Updated JSON Schema limitations: Nested levels increases from 5 to 10 Max properties increases from 100 to 500 Enabled...