Releasesby GlyphAdded preview support for Z.ai GLM 4.6: zai-glm-4.6
Added preview support for Z.ai GLM 4.6: zai-glm-4.6
Also shipped Nov 7, 2025Cerebras in November 2025 →
Reduced compute pricing, more projects on Free plan, AI-powered onboarding release - Nov 07, 2025
Reduced compute pricing across Launch, Scale, and Agent plans. We've reduced compute pricing by up to 25% across our plans Launch plan Now $0.106 per CU hour (p...
What's new in Sigma
Data apps If/else control flow in action sequences (GA) If/else control flow is now generally available. Use if/else statements to create dynamic workflows within action sequences. If/else control flow adds flexibility to a sequence by allowing it to check one or more conditions and execute actions for the first condition that evaluates to true.
Workers automatic tracing, now in open beta
Enable automatic tracing on your Workers, giving you detailed metadata and timing information for every operation your Worker performs. Tracing helps you identify performance bottlenecks, resolve errors, and understand how your Worker interacts with other services on the Workers platform.
The little things, week ending November 7, 2025
A collection of updates to Replicate for the week ending November 7, 2025.
Expanded Language Detection: Now Supports 35 Languages for Pre-Recorded Audio
Language Detection for pre-recorded (batch) audio now supports 35 languages (previously 16), allowing you to automatically detect and transcribe a much broader array of languages with one request. Enable broader coverage by setting detect_language=true in your API call.
Cache - Inspect Cache Keys with Cloudflare Trace
You can now see the exact cache key generated for any request directly in Cloudflare Trace. This visibility helps you troubleshoot cache hits and misses, and verify that your Custom Cache Keys , configured via Cache Rules or Page Rules , are working as intended. Previously, diagnosing caching behavior required inferring the key from configuration settings.
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.
Added support for prompt caching, which automatically stores and reuses prompt prefixes to reduce latency and...
Added support for prompt caching, which automatically stores and reuses prompt prefixes to reduce latency and improve time to first token for similar requests. Learn more in our Prompt Caching guide.