Releasesby GlyphNew serverless models
The following models are now available on serverless : MiniMaxAI/MiniMax-H3 : Pricing: $0.1391/sec at 2k.
Also shipped Sep 14, 2026Together AI in September 2026 →
Metadata for BigQuery Graph is automatically ingested and searchable in Knowledge Catalog
Metadata for BigQuery Graph is automatically ingested and searchable in Knowledge Catalog . This feature is available in preview .
BigQuery supports WHERE clauses inside aggregate function calls in preview
Aggregate function calls can now include a WHERE clause that filters their input with a boolean expression, simplifying conditional aggregation in SQL.
Multimodal AI_SUMMARIZE for automatic theme summarization (Public Preview)
Snowflake Cortex AI_SUMMARIZE is now available in public preview, enabling customers to summarize text and multimodal content, including images and documents, directly in Snowflake.
Zero-copy support for all table formats in interactive warehouses (General availability)
Support for all table formats in interactive warehouses is now generally available and is no longer in Preview .
Genie visualizations in Slack replies (Public Preview)
When a Genie response includes a chart, the visualization now appears as an image in the Slack reply. If you installed the Databricks Genie app for Slack previously, reinstall it to enable this. See Visualizations .
Metadata for BigQuery Graph is now automatically ingested and searchable in Knowledge Catalog
Metadata for BigQuery Graph is now automatically ingested and searchable in Knowledge Catalog. This feature is available in preview . For more information, see Knowledge Catalog overview .
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.
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 .
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 : 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.