Cerebras Release notes and new features

Public · Sunnyvale, US · 45 releases · 3 this month

Also onTechConf(1 conference)

Cerebras releases

September 2026 digest

45 releases

Date	Release	Product	Type
Sep 22	Temporary increase to Qwen 3.8 27B total token rate limit The Developer tier total token rate limit for...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Sep 3	Gemma 4 31B availability changes on public endpoints Starting September 3, 2026, gemma-4-31b is no longer...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Sep 3	Qwen 3.8 27B available on public endpoints qwen-3.8-27b is now available on Cerebras public endpointsunverified Cerebras InferenceUpdate	Cerebras Inference	Update
Aug 28	Flowise integration moved to legacy status Flowise has archived its repositories and ends official support on...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Jul 27	GLM 4.7 reasoning_logprobs default will not ship before deprecation zai-glm-4.7 is scheduled for deprecation...unverified Cerebras InferenceDeprecation	Cerebras Inference	Deprecation
Jul 26	Image dimension limit for image inputs Image inputs now enforce a maximum width and height of 15,000 pixels...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Jul 24	Predicted Outputs limited to dedicated endpoints Predicted Outputs is available by request on dedicated...unverified Cerebras InferencePreview	Cerebras Inference	Preview
Jul 23	Image limit increased for Developer and Enterprise accounts Developer and Enterprise accounts using...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Jul 22	API Version 2 Default Rollout As of July 22, 2026, API version 2 is the defaultunverified Cerebras InferenceUpdate	Cerebras Inference	Update
Jul 16	Free Trial credits for new accounts New accounts now receive \$5 in free credits after adding a verified...unverified Cerebras InferencePricing	Cerebras Inference	Pricing
Jul 16	Uncached Rate Limits Cerebras now uses a dual-bucket rate limiting modelunverified Cerebras InferenceUpdate	Cerebras Inference	Update
Jul 14	Gemma 4 31B available across coding integrations gemma-4-31b is now a selectable model in our Cline, Kilo...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Jun 29	Gemma 4 31B and Image Input Support - Gemma 4 31B (gemma-4-31b) is now available in previewunverified Cerebras InferencePreview	Cerebras Inference	Preview
Jun 1	New dedicated models: StepFun Step 3.5 Flash and Step 3.7 Flash StepFun's Step 3.5 Flash and Step 3.7 Flash...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
May 1	Projects is now generally available Projects is out of private preview and available to all organizationsunverified Cerebras InferenceGA	Cerebras Inference	GA
Apr 27	New dedicated models: GLM 5, GLM 5.1, and Kimi K2.6 Z.AI's GLM 5 and GLM 5.1 and Moonshot AI's Kimi K2.6 are...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Apr 24	Validation Errors Now Return 400 Instead of 422 API requests that fail validation now return HTTP 400 Bad...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Apr 22	New parameter: prompt_cache_key /v1/chat/completions and /v1/completions now accept an optional...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Apr 10	Payload Optimization: msgpack and gzip /v1/chat/completions and /v1/completions now accept request bodies...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Mar 31	New Sampling Parameters The following parameters are now available on all models: - frequency_penalty –...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Mar 30	Streaming: Server-Sent Events (SSE) Streaming responses for Chat Completions (/v1/chat/completions) and...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Mar 27	Rolling out selective 4-bit weight-only quantization for supported models, targeting non-sensitive layers...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Mar 26	developer Message Role (gpt-oss-120b) The Chat Completions API now supports the developer message role for...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Mar 26	Temperature Parameter: Increased Maximum The maximum allowed value for the temperature parameter for Chat...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Mar 25	Logprob Consistency Logprobs are now computed from the model's raw output, before applying temperature scalingunverified Cerebras InferenceUpdate	Cerebras Inference	Update
Mar 24	Deprecating disable_reasoning parameter for zai-glm-4.7 The disable_reasoning parameter is deprecated and...unverified Cerebras InferenceDeprecation	Cerebras Inference	Deprecation
Feb 27	reasoning_effort="none" support for GLM 4.7 zai-glm-4.7 now accepts the reasoning_effort parameterunverified Cerebras InferenceUpdate	Cerebras Inference	Update
Jan 22	Monitor your dedicated inference endpoints with the new Metrics API, providing Prometheus-compatible metrics...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Jan 21	API Version 2 Available for Testing API version 2 is now available for testing via the...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Jan 14	Prioritize requests to the API to balance latency sensitivity and resource allocation across your workloads...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Jan 9	Constrained Decoding Generally Available Constrained decoding has moved to General Availability (GA) with...unverified Cerebras InferenceGA	Cerebras Inference	GA
Jan 6	Added preview support for Z.ai GLM 4.7: zai-glm-4.7unverified Cerebras InferencePreview	Cerebras Inference	Preview
Dec 18	Process large-scale inference workloads asynchronously with the new Batch API and Files APIunverified Cerebras InferenceUpdate	Cerebras Inference	Update
Dec 17	Added support for parallel tool calling, allowing models to request multiple tool invocations simultaneously...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Dec 16	Streaming Support Streaming is now supported for all models, including with structured output requests...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Dec 10	Added support for prompt caching, which automatically stores and reuses prompt prefixes to reduce latency and...unverified Cerebras InferenceUpdate	Cerebras Inference	Update
Nov 24	We now support Predicted Outputs for faster generation when large portions of the output are known in advanceunverified Cerebras InferenceUpdate	Cerebras Inference	Update
Nov 14	Deprecated qwen-3-235b-a22b-thinking-2507 We recommend migrating to GPT OSS 120Bunverified Cerebras InferenceDeprecation	Cerebras Inference	Deprecation
Nov 7	Added preview support for Z.ai GLM 4.6: zai-glm-4.6unverified Cerebras InferencePreview	Cerebras Inference	Preview
Nov 5	Deprecated qwen-3-coder-480bunverified Cerebras InferenceDeprecation	Cerebras Inference	Deprecation
Nov 3	Deprecated llama-4-scout-17b-16e-instruct See Deprecations for more detailsunverified Cerebras InferenceDeprecation	Cerebras Inference	Deprecation
Oct 22	Added support for retrieving log probabilities via the logprobs parameter for the Completions endpointunverified Cerebras InferenceUpdate	Cerebras Inference	Update
Oct 15	Deprecated llama-4-maverick-17b-128e-instruct See Deprecations for more detailsunverified Cerebras InferenceDeprecation	Cerebras Inference	Deprecation
Oct 6	We're gradually introducing multi-token streaming across our modelsunverified Cerebras InferenceUpdate	Cerebras Inference	Update
Oct 2	Updated support for OpenAI GPT-OSS (gpt-oss-120b) - Tool calling with strict: true (constrained decoding) -...unverified Cerebras InferenceUpdate	Cerebras Inference	Update

About and activity

Cerebras Systems Inc., headquartered in Sunnyvale, California, develops semiconductors, supercomputers, and related software to power artificial intelligence deep-learning applications such as inference engines.

Company profile

Releases per month

4Apr 1May 2Jun 8Jul 1Aug 3Sep

Sources: each vendor's own release notes, changelogs and GitHub releases, read daily to monthly by how often it posts. Logos via logo.dev; trademarks belong to their owners.

Cerebras releases

New releases by email