Releasesby GlyphPricing update
H100 80GB dedicated endpoint hardware is now $3.99 per hour, down from $5.49. See Dedicated endpoint pricing .
Also shipped Sep 1, 2026Together AI in September 2026 →
Fivetran connection cron scheduling enters beta
Connections can now use one or more cron expressions to control exactly when they sync, giving finer control than fixed sync frequencies.
Fivetran Connection Warnings REST API enters private preview
New endpoints retrieve active warnings for a connection, grouped by destination table with codes, messages and timestamps, and dismiss all instances of a warning type, enabling programmatic warning management.
Snowflake App Runtime (General availability)
Snowflake App Runtime is now generally available and is no longer in Preview .
Apache Arrow support for Zerobus Ingest is now generally available
Apache Arrow support for Zerobus Ingest in Lakeflow Connect is now generally available. See Use Arrow Flight with Zerobus Ingest .
Genie One web search is in Beta
Genie One can now search the public web to answer questions that need current information, such as recent release notes, third-party documentation, or news. Genie One cites the external sources it uses as links in its response. See Search the web .
More from Together AI platformEvery Together AI platform release →
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 .
New 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).
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 .