Releasesby GlyphBatch jobs in the CLI
The Together CLI now includes a tg batches command group for batch inference : tg batches submit uploads a local JSONL file (or takes an existing file ID) and creates a job against chat.completions , audio.transcriptions , or audio.translations . tg batches list , retrieve , and cancel manage the job lifecycle, with ls and get as aliases.
Also shipped Aug 26, 2026Together AI in August 2026 →
You can now view real-time logs for your Python UDFs in Cloud Logging
You can now view real-time logs for your Python UDFs in Cloud Logging. This feature is generally available .
Cortex Extension references in agent skills (General availability)
Referencing a Cortex Extension from an agent skill is now generally available. Set the skill source type to CORTEX_EXTENSION and path to the extension's fully qualified name, and Snowflake expands the reference into the extension's member skills at request time, so you don't list each skill individually.
Cortex Agents Coding Agent (General availability)
The Cortex Agents Coding Agent is now generally available. Add the code_toolset_all tool type to a Cortex Agent, and Snowflake provisions and manages a sandbox backed by the same runtime that powers Snowflake CoCo: bash, file read/write/edit, grep, glob, web search, SQL execution, and skills.
Organization user types (General availability)
With this release, you can specify whether an organization user represents a person or a service. Set the TYPE property to SERVICE for a service or application that interacts with Snowflake without human interaction. If you don't specify a type, the organization user is a PERSON user, which matches the previous behavior.
Semantic Studio (Preview)
Semantic Studio is now available in public preview for all accounts. Semantic Studio is the authoring environment for semantic views in Workspaces, combining conversational authoring with CoCo, direct YAML editing, and deployment to the live Snowflake object in a single surface.
Zerobus Ingest into streaming tables is now generally available
Ingesting into streaming tables with Zerobus Ingest in Lakeflow Connect is now generally available. Writing to a streaming table works the same way as writing to a managed Delta table, with the same limits and quotas. See Create or identify the target table .
More from Together AI platformEvery Together AI platform release →
New serverless models
The following models are now available on serverless : zai-org/GLM-5.3-Flash : 1,000,000 context length, FP8 quantization, function calling and structured outputs. Pricing: $0.15 input / $0.50 output / $0.03 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 .
Model deprecations
The following models have been deprecated and are no longer available on serverless: nvidia/Nemotron-3-ultra-550b-a55b . pearl-ai/gemma-4-31b-it . deepseek-ai/DeepSeek-V4-Pro . Use deepseek-ai/DeepSeek-V4-Pro-0813 instead. moonshotai/Kimi-K2.7-Code .
Model deprecations
The following models have been deprecated and are no longer available on serverless: google/gemma-3n-E4B-it . meta-llama/Llama-Guard-4-12B . These models are not supported by on-demand dedicated endpoints. See Deprecations for migration options.
New models available for fine-tuning
You can now fine-tune the following models: Qwen/Qwen3.8-27B . See Supported models for the full list.