Releasesby GlyphNew serverless models
The following models are now available on serverless : Qwen/Qwen3.8-Flash : 1,000,000 context length. Pricing: $0.15 input / $0.47 output (per 1M tokens).
Also shipped Aug 31, 2026Together AI in August 2026 →
You can now create, store , and manage pipelines in Git folders
You can now create, store , and manage pipelines in Git folders. This feature is in Preview .
BigQuery now supports TabFM , Google's pre-trained foundation model for tabular data
BigQuery now supports TabFM , Google's pre-trained foundation model for tabular data. TabFM enables zero-shot regression and classification through in-context learning. It delivers high-accuracy predictions on structured data without requiring model training or hyperparameter tuning.
You can now create an identity column , sometimes referred to as an auto-incrementing column, on a table
You can now create an identity column , sometimes referred to as an auto-incrementing column, on a table. You can use identity columns to create and maintain primary keys on your tables. When you insert a row into a table that has an identity column, BigQuery generates a unique integer value for that column. This feature is in Preview .
BigQuery Graph is generally available (GA)
BigQuery Graph is generally available (GA). BigQuery Graph now includes support for the CALL graph query statement , and the following path inspection GQL functions : IS_ACYCLIC IS_SIMPLE IS_TRAIL .
app.yml for Snowflake App Runtime (Preview)
Snowflake App Runtime projects use a single app.yml file to describe both deployment and the remote build. Include version: 2 at the top of the file. snow app setup writes this file for new projects.
More from Together AI platformEvery Together AI platform release →
Pricing update
H100 80GB dedicated endpoint hardware is now $3.99 per hour, down from $5.49. See Dedicated endpoint pricing .
Model deprecations
The following models are deprecated and will be removed from serverless on September 14, 2026: openai/gpt-oss-20b . Recommended replacement: Qwen/Qwen3.5-9B . google/gemma-4-31B-it . Recommended replacement: zai-org/GLM-5.3-Flash . thinkingmachines/Inkling-Small . Recommended replacement: zai-org/GLM-5.3-Flash . intfloat/multilingual-e5-large-instruct .
active_sessions autoscaling metric for TTS
Dedicated endpoint autoscaling now accepts active_sessions , which targets concurrent open client WebSocket sessions per replica on a TTS deployment ( AVERAGE_VALUE only). The default inflight_requests metric also covers TTS handlers, so HTTP TTS traffic can keep scaling without a policy change. See Configure autoscaling .
New serverless models
The following models are now available on serverless : zai-org/GLM-5.3 : 1,000,000 context length, FP4 quantization, function calling and structured outputs. Pricing: $1.40 input / $4.40 output / $0.26 cached input (per 1M tokens).
Billing usage API (beta)
GET /billing/usage returns organization-wide usage and cost line items, filterable by month. The endpoint is in beta and enabled per organization. See Get billing usage .
File upload progress in the CLI and Python SDK
tg files upload and tg files check now show a progress bar in interactive terminals. The Python SDK accepts an optional progress_callback on client.files.upload() that receives upload progress events. See the files CLI reference and Data preparation .
Slurm cluster kubeconfig for project members
Project members can now download the cluster kubeconfig for Slurm clusters from the cluster details page, matching Kubernetes cluster behavior. See Download cluster kubeconfig .
Legacy API key regeneration
Legacy API keys can now be regenerated by any admin or editor of the default project. Legacy keys appear in the project's API keys table with a Deprecated badge. See Legacy API keys .