Releasesby GlyphNew models available for fine-tuning
You can now fine-tune the following models: zai-org/GLM-5.3 . See Supported models for the full list.
Also shipped Sep 8, 2026Together AI in September 2026 →
Conversational analytics now supports predictive modeling questions using the AI.PREDICT function
Conversational analytics now supports predictive modeling questions using the AI.PREDICT function . This feature is in Preview .
Add and drop hybrid table constraints online (General availability)
With this release, you can add and drop UNIQUE and FOREIGN KEY constraints on an existing hybrid table by using alter table . Previously, you had to define these constraints when you created the table, so adding a foreign key to a table that was already serving a workload meant recreating and reloading the table.
Shadow traffic for gateways (Preview)
With this preview release, you can use a shadow traffic gateway to send all production requests to a primary service endpoint while mirroring a percentage of those requests to one or more shadow endpoints. Responses from shadow endpoints aren't returned to clients.
The partner-powered AI features setting will be removed
On November 1, 2026, Databricks will remove the account- and workspace-level toggle for partner-powered AI features. Each workspace will keep its current setting value: if the setting is enabled, it stays enabled, and if it's disabled, it stays disabled. Removing the toggle doesn't change any setting values.
Incremental ingestion for Salesforce formula fields in Lakeflow Connect will soon be generally available
Incremental ingestion for Salesforce formula fields in Lakeflow Connect will soon be generally available. Today, Lakeflow Connect ingests formula fields by taking a full snapshot on each pipeline run by default. When incremental formula field ingestion is generally available, full snapshots will no longer be the default.
ABAC DENY policies are in Beta
ABAC DENY policies are in Beta in Unity Catalog. DENY policies can be used to explicitly deny the MANAGE ACCESS CONTROL privilege to prevent specified principals, including object owners, from performing access-management operations. They always take precedence over any grant. For details, see ABAC DENY policies (Beta) .
More from Together AI platformEvery Together AI platform release →
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.
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).
New serverless models
The following models are now available on serverless : MiniMaxAI/MiniMax-H3 : Pricing: $0.1391/sec at 2k.
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.
Model 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 .