Releasesby GlyphImage limit increased for Developer and Enterprise accounts Developer and Enterprise accounts using...
Image limit increased for Developer and Enterprise accounts Developer and Enterprise accounts using gemma-4-31b on public endpoints can now include up to 10 images in a single request, increased from 5. Free Trial accounts remain limited to 2 images per request.
Also shipped Jul 23, 2026Cerebras in July 2026 →
SQL environment variable and private Git package support for dbt Projects on Snowflake
Environment variable support for dbt Projects on Snowflake is now generally available. Manage per-developer schemas, dynamic runtime values, secrets, and multiple environments in a single, Git-versioned env.yml file that Snowflake resolves before each run.
SERVICE_AGENT user type (General availability)
With this release, the SERVICE_AGENT user type is generally available. Use this user type for automated AI agents that interact with Snowflake using their own identity and privileges.
SHOW CORTEX BASE MODELS command (General availability)
With this release, we are pleased to announce the general availability of the SHOW CORTEX BASE MODELS command. Use this command to list the Cortex Base Models available in your account, along with each model’s lifecycle status, regional availability, legacy date, and end-of-life date.
C++ SDK for the Zerobus Ingest connector is now available in Beta
A C++ SDK for the Zerobus Ingest connector in Lakeflow Connect is now available in Beta. The SDK provides a high-throughput gRPC client for ingesting records directly into Unity Catalog Delta tables, with support for JSON and Protocol Buffers. See Use Zerobus Ingest .
Genie Code scheduled tasks are in Beta
You can now schedule Genie Code to run a prompt on a recurring schedule. Each run executes your prompt as a full Genie Code session and produces a continuable Genie chat with the results, so you can turn recurring analysis into an unattended background task. Create a scheduled task by asking Genie Code in chat or by filling in the create form manually.
Databricks Runtime 19 and Databricks Runtime 19 for Machine Learning are now generally available
Databricks Runtime 19 and Databricks Runtime 19 for Machine Learning are now generally available (GA), powered by Apache Spark 4.2.0. For release notes, see Databricks Runtime 19 and Databricks Runtime 19 for Machine Learning .
More from Cerebras InferenceEvery Cerebras Inference release →
Predicted Outputs limited to dedicated endpoints Predicted Outputs is available by request on dedicated...
Predicted Outputs limited to dedicated endpoints Predicted Outputs is available by request on dedicated endpoints. To request it for your endpoint, contact us or reach out to your account representative. You can also try Predicted Outputs with gpt-oss-120b in Public Preview using a Free Trial or Developer account.
API Version 2 Default Rollout As of July 22, 2026, API version 2 is the default
API Version 2 Default Rollout As of July 22, 2026, API version 2 is the default. Version 2 includes: Stricter schema validation for structured outputs Stricter validation for multi-turn tool-calling messages A separate reasoning_logprobs response field for reasoning-token logprobs Corrected Unicode handling in logprobs Z.ai GLM 4.7 is scheduled for...
Image dimension limit for image inputs Image inputs now enforce a maximum width and height of 15,000 pixels...
Image dimension limit for image inputs Image inputs now enforce a maximum width and height of 15,000 pixels per side. Requests with larger images return 413 Content Too Large with the message "Image dimensions {width}x{height} exceed the 15000px per-side limit". Existing payload-size, image-count, and decompressed-memory limits are unchanged.
GLM 4.7 reasoning_logprobs default will not ship before deprecation zai-glm-4.7 is scheduled for deprecation...
GLM 4.7 reasoning_logprobs default will not ship before deprecation zai-glm-4.7 is scheduled for deprecation on August 17, 2026 and will keep its existing default logprobs response shape until then. Requests that explicitly set the X-Cerebras-Version-Patch: 2 header still receive the separated reasoning_logprobs field.
Free Trial credits for new accounts New accounts now receive \$5 in free credits after adding a verified...
Free Trial credits for new accounts New accounts now receive \$5 in free credits after adding a verified payment method. Credits work across all models on public endpoints and expire 30 days after Cerebras grants them. You aren't charged unless you purchase additional credits.
Uncached Rate Limits Cerebras now uses a dual-bucket rate limiting model
Uncached Rate Limits Cerebras now uses a dual-bucket rate limiting model. Every organization has two independent token limits: Uncached TPM , tokens that require full compute (cache misses). Total TPM , uncached + cached tokens combined.
Gemma 4 31B available across coding integrations gemma-4-31b is now a selectable model in our Cline, Kilo...
Gemma 4 31B available across coding integrations gemma-4-31b is now a selectable model in our Cline, Kilo Code, opencode, and VS Code integration guides. Gemma 4 31B adds multimodal support to coding workflows , you can pass screenshots, diagrams, and design assets alongside text prompts.
Gemma 4 31B and Image Input Support - Gemma 4 31B (gemma-4-31b) is now available in preview
Gemma 4 31B and Image Input Support Gemma 4 31B (gemma-4-31b) is now available in preview. It's the first model on Cerebras to support image input. Send screenshots, documents, diagrams, and design assets alongside text using the standard Chat Completions API. Image Inputs are now available in Public Preview through the Chat Completions API.