Releasesby GlyphPreemptible 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.
Also shipped Sep 10, 2026Together AI in September 2026 →
BigQuery conversational analytics adds ML.CORRELATION in preview
Conversational analytics can now use ML.CORRELATION to calculate statistical correlations between a target column and one or more metric columns in a table.
BigQuery ML.METRICS evaluates predictions without a stored model
The preview ML.METRICS function computes classification or regression evaluation metrics on any table or query with actual and predicted values, with no need to create or reference a stored model.
You can use the AI.CAUSAL_EFFECT function to quantify the impact of specific interventions on time series data
You can use the AI.CAUSAL_EFFECT function to quantify the impact of specific interventions on time series data. This feature is in Preview .
BigQuery Data Engineering Agent integrates with BigQuery Graph
The Data Engineering Agent now uses BigQuery Graph for extra context between source and destination schemas, improving schema mapping accuracy in data engineering pipelines. It is generally available.
Using dbt artifacts for Slim CI and defer to production in dbt Projects on Snowflake (General availability)
Slim CI, defer to production, failed-execution recovery, and concurrent execution are now generally available for dbt Projects on Snowflake. Reuse dbt artifacts from recent production executions to accelerate development, streamline CI/CD workflows, and recover from failed production runs without maintaining a separate artifact store.
External secret providers (Preview)
External secret providers are now in preview. If your organization already keeps API keys, database passwords, and similar values in AWS Secrets Manager, Azure Key Vault, or Google Cloud Secret Manager, Snowflake can read those values when a query needs them, so you don't have to maintain a second copy in a Snowflake secret .
More from Together AI platformEvery Together AI platform release →
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 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.
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 .