Releasesby GlyphAdded 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.
Also shipped Dec 10, 2025Cerebras in December 2025 →
AI Crawl Control - Pay Per Crawl (Private beta) - Discovery API, custom pricing, and advanced configuration
Pay Per Crawl is introducing enhancements for both AI crawler operators and site owners, focusing on programmatic discovery, flexible pricing models, and granular configuration control. For AI crawler operators Discovery API A new authenticated API endpoint allows verified crawlers to programmatically discover domains participating in Pay Per Crawl.
Introducing the Cross-cluster UI Public Preview
As organizations scale their cloud-native infrastructure, the number of Kubernetes clusters grows exponentially. Managing these environments individually creates silos, making it difficult for Platform Engineers and DevOps teams to understand their fleet's overall health.
Requesting App for Cross App Access (XAA) is now available in Beta
This new Token Vault capability allows Client Applications to obtain access tokens from third-party APIs (resource servers), through an authorization flow that is coordinated by a common Identity Provider implementing the [Identity Assertion Authorisation Grant](https://datatracker.ietf.org/doc/draft-ietf-oauth-identity-assertion-authz-grant/) standard.
Container Images (release 251210)
- quay.io/deepgram/self-hosted-api:release-251210 Equivalent image to: quay.io/deepgram/self-hosted-api:1.172.2 quay.io/deepgram/self-hosted-engine:release-251210 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.104.10 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-251210 Equivalent image...
This Release Contains The Following Changes
- Expands Nova-3 with 10 New Languages , Building on the 11-language expansion from the 251118 release, Nova-3 now supports 31 total languages. This release adds 10 additional languages, bringing improved accuracy and contextual understanding across: Southern and Eastern Europe : Greek (el), Romanian (ro), Slovak (sk), Catalan (ca) Northern and Baltic...
WAF Release - 2025-12-10 - Emergency
This additional week's emergency release introduces improvements to our existing rule for React – Remote Code Execution – CVE-2025-55182 - 2, along with two new generic detections covering server-side function exposure and resource-exhaustion patterns.
More from Cerebras InferenceEvery Cerebras Inference release →
Streaming Support Streaming is now supported for all models, including with structured output requests...
Streaming Support Streaming is now supported for all models, including with structured output requests (response_format, tools). Reasoning Format Controls Added reasoning_format parameter for reasoning models, giving you control over how reasoning text appears in responses.
Added support for parallel tool calling, allowing models to request multiple tool invocations simultaneously...
Added support for parallel tool calling, allowing models to request multiple tool invocations simultaneously in a single response. This reduces latency when handling queries that require multiple independent operations. Learn more in our Tool Calling guide.
Process large-scale inference workloads asynchronously with the new Batch API and Files API
Process large-scale inference workloads asynchronously with the new Batch API and Files API. Submit up to 50,000 requests in a single batch job and get 50% cost savings. Learn more in our Batch guide.
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.
Constrained Decoding Generally Available Constrained decoding has moved to General Availability (GA) with...
Constrained Decoding Generally Available Constrained decoding has moved to General Availability (GA) with expanded capabilities. Supported models Structured Outputs and Tool Calling with strict: true are now available on the following models: gpt-oss-120b llama-3.1-8b qwen-3-235b-a22b-instruct-2507 qwen-3-32b zai-glm-4.6 zai-glm-4.7 New capabilities...