Releasesby GlyphModel deprecations
The following models have been deprecated and are no longer available on serverless: openai/gpt-oss-20b . Recommended replacement: Qwen/Qwen3.5-9B . Supported by on-demand dedicated endpoints. google/gemma-4-31B-it . Recommended replacement: zai-org/GLM-5.3-Flash . Supported by on-demand dedicated endpoints. thinkingmachines/Inkling-Small .
Also shipped Sep 15, 2026Together AI in September 2026 →
Predict dynamic table refresh behavior with EXPLAIN CHANGES (General availability)
You can now use EXPLAIN CHANGES to predict a dynamic table's refresh behavior before it happens, either for a manual refresh or as part of a DDL change, without applying the change.
Horizon Catalog Explorer UI (Preview)
With this release, the Horizon Catalog Explorer is the default experience for browsing Snowflake objects in Snowsight, replacing Database Explorer. The Horizon Catalog Explorer provides consistent navigation and object detail pages while preserving the tabs and actions that you already use.
Embedding Streamlit in Snowflake apps in external pages (General availability)
Embedding Streamlit in Snowflake apps in external pages is now generally available. You can render a container-runtime app inside a page you host, such as a customer portal or an internal dashboard, using a single tag.
Elastic Channels for Snowpipe Streaming (General availability)
Elastic Channels for Snowpipe Streaming are now generally available. Elastic Channels provide one implicit, server-scaled ingestion path per pipe, so concurrent producers can stream directly to Snowflake tables and supported Snowflake-managed Iceberg tables without managing channel names, lifecycle, ordering, or offset tokens.
Webhook-triggered deployments for Databricks Apps will soon be generally available
Starting in October 2026, webhook-triggered deployments for Databricks Apps will be generally available. Automatically deploy your app when changes are pushed to a connected GitHub or Azure DevOps repository, so your deployed app stays in sync with your repository without manual redeployment. See Deploy a Databricks app .
Sharing foreign Delta tables with OpenSharing is now generally available
Sharing and reading foreign Delta tables with OpenSharing is now generally available. Providers can share Delta-format tables federated from OneLake, a Hive metastore, or AWS Glue, without copying data into Databricks. See Add foreign Delta tables to a share .
More from Together AI platformEvery Together AI platform release →
Rollouts for dedicated model inference
Rollouts shift live traffic from one deployment to another under the same endpoint, without changing the endpoint URL. Pick a canary, blue-green, or rolling strategy to determine how traffic moves, and optionally gate a canary rollout on live metrics so it pauses automatically if the new deployment regresses.
Together CLI v2.34.0
Version 2.34.0 of the Together CLI and Python SDK carries the rollouts release above (the SDK surface is client.beta.endpoints.rollouts ) and also adds: HIPAA placement : tg beta endpoints deploy accepts --placement.hipaa to restrict a deployment to HIPAA-attested clusters. The Python SDK takes the same policy as compliance_policy on inline placement.
Automatic idle shutdown for dedicated deployments
Deployments can now stop themselves when they go unused. Set an inactivity timeout with --inactive-timeout (the inactiveTimeout field in the management API), and if the deployment serves no inference requests for that many minutes, it scales to zero replicas, releasing its hardware and stopping billing. See Automatic idle shutdown .
New serverless models
The following models are now available on serverless : MiniMaxAI/MiniMax-H3 : Pricing: $0.1391/sec at 2k.
New serverless models
The following models are now available on serverless : deepseek-ai/DeepSeek-V4.1-Flash : 1,000,000 context length, FP8 quantization, function calling, and structured outputs. Pricing: $0.30 input / $1.20 output / $0.006 cached input (per 1M tokens).
Preemptible compute for GPU clusters
Preemptible compute is now in public preview for Kubernetes GPU clusters. Alongside standard nodes, you can set a preemptible GPU target, and Together provisions toward it as spare capacity becomes available, at a flat discounted rate relative to on-demand.
What's new:
- Preemptible GPU targets: Set num_preemptible_gpus at cluster create or update from the console, CLI, or API. Together automatically provisions replacements toward the target after nodes are reclaimed.
Together CLI v2.33.2
Version 2.33.2 of the Together CLI improves error reporting and upload feedback: Endpoint, fine-tuning, and model commands now print the API's error message when a request fails, rather than a generic failure notice. The same goes for a missing API key or command argument.