Releasesby GlyphPost-training: Kimi K3.1 Pro
Together AI now supports LoRA post-training for the Kimi K3.1 Pro model with a 163,840-token training context.
Also shipped Nov 4, 2026Together AI in November 2026 →
[Launched] Generally Available: Azure Database for PostgreSQL stable REST API version 2026-10-01
The Azure Database for PostgreSQL Flexible Server REST API version 2026-10-01 is now generally available, introducing new capabilities for maintenance, immutable backups, and encryption.
Analytics API (Public preview): report on the health of the data behind your agents, from your AI tool
The Monte Carlo Analytics API is now in public preview, allowing users to query data health, alert status, and cost metrics directly from AI tools via the Monte Carlo MCP server.
Twice the included embedding tokens through December 31
Pinecone is doubling the included monthly embedding tokens for Starter and Builder organizations through December 31, 2026.
Gemini Enterprise: Switch between teams in the mobile app
The Gemini Enterprise mobile app now supports switching between multiple teams without re-authentication, and allows renaming or removing teams from the list.
Compare AI agent changes with Online Experiments in Agent Observability
Datadog Online Experiments allows engineers to test AI agent changes against production traffic. It enables comparison of response quality, cost, latency, and error rates.
Postmortems End of Life Completed
The Postmortems feature has been retired in favor of the upgraded Post-Incident Reviews in the PagerDuty web UI.
More from Together AI platformEvery Together AI platform release →
New serverless models
Together AI added the moonshotai/Kimi-K3.1-Pro model to its serverless platform, supporting a 1M token context window, function calling, and structured outputs.
Messages API and Responses API
Together AI now supports the Anthropic Messages API at POST /v1/messages and the OpenAI Responses API at POST /v1/responses . To run an app built on either API on Together, change its API key, base URL, and model.
Post-training: FP4 preparation for MiniMax M3.1 Flash
You can now deploy a MiniMax M3.1 Flash adapter on dedicated model inference by first preparing it for FP4 inference . The base model already ships in its serving format, so the job only merges the adapter, which takes about 1 hour.
Together Python SDK and CLI 3.1.0
Together Python SDK 3.1.0 and Together CLI 3.1.0 are now available.
What's new:
- Deploy after tg login : tg beta jig deploy now works with a tg login session, so you don't need an API key to deploy a container . Expiring secrets: client.beta.jig.secrets.create and update take ttl_seconds , which sets how long a secret lives before it's deleted, from one to 14 days. Secrets return their deletion time as expires_at .
Post-training: MiniMax M3 retired
MiniMaxAI/MiniMax-M3 is no longer available for new post-training model resources. Use MiniMaxAI/MiniMax-M3.1-Flash instead. Existing MiniMax M3 model resources keep running, and their checkpoints stay available for download. See Supported models .
Post-training: GLM-5.3 Flash
zai-org/GLM-5.3-Flash is available for post-training : LoRA training on B200-SXM , a 159,744-token training context, a 163,840-token generator context, rank up to 32, and up to five adapter sessions per resource. The cookbook renders its prompts with the GLM codec.
Post-training: MiniMax M3.1 Flash
Together AI now supports LoRA training for the MiniMax M3.1 Flash model, featuring a 262,144-token context window.