Releasesby GlyphNew dedicated endpoint models
The following models are now available for deployment on dedicated endpoints : deepseek-ai/DeepSeek-V4.1-Flash-1017 .
Also shipped Oct 18, 2026Together AI in October 2026 →
Training Upcoming Serverless Training deprecation: DeepSeek V4 Flash (0731) On November 2, 2026 , DeepSeek V4...
Training Upcoming Serverless Training deprecation: DeepSeek V4 Flash (0731) On November 2, 2026 , DeepSeek V4 Flash (0731) will be removed from the shared Serverless Training pool. This change applies only to Serverless Training. If you train DeepSeek V4 Flash (0731) on Serverless Training, migrate to DeepSeek V4.1 Flash 1017 before November 2, 2026.
feldera 0.367.0
- [pipeline-manager] expose the user creation time in /config/session [adapters] Reject JSON update format redis for input. Drop the YAML copy of the pipeline configuration [adapters] Read the operation of raw Avro input from cdc_field [web-console] Combine the storage status with the clear storage button [dbsp] Keep an old subcircuit live during a...
Ollama 0.40.7
- pplx-decider is a 27B decision model from Perplexity, fine-tuned from Qwen3.8-27B - Continuing an OpenAI-compatible Responses conversation no longer fails when switching between models with and without thinking, or when the history contains another provider's compaction items - Fixed streaming Responses requests where client tool calls (e.g.
Request edit access to a project you can only view
You can now ask for edit access without leaving the project. Select Request to edit at the top of the project and add an optional message. Lovable emails the project's owner, or the workspace's admins and owners, who can approve or deny the request.
vLLM 0.32.0
v0.32.0 Highlights This release features 814 commits from 363 contributors (121 new)! - Structured decisions and generic parsers: the new POST /v1/systemone endpoint answers choice, noul and score questions over a structured state , is served by default (#60677, #60696), and also runs on Cloudflare/clef-omni , LiquidAI/d1-3B and DiffusionGemma .
More from Together AI platformEvery Together AI platform release →
New serverless models
The following models are now available on serverless : deepseek-ai/DeepSeek-V4.1-Flash-1017 : 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 dedicated endpoint models
The following models are now available for deployment on dedicated endpoints : moonshotai/Kimi-K3 .
Longer post-training context for Kimi K3
moonshotai/Kimi-K3 on post-training now supports a 163,840-token training context (up from 65,536) and a 167,936-token generator context (up from 69,632). See Supported models .
Post-training: Muse Spark Open
meta-models/Muse-Spark-Open-816B-A42B 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 one adapter session per resource. See Supported models .
New serverless models
The following models are now available on serverless : reflection/Beam-1.0-501B-A23B : 1,048,576 context length, NVFP4 quantization, function calling, and structured outputs. Pricing: $0.40 input / $1.20 output / $0.04 cached input (per 1M tokens).
Geo-specific inference
You can now keep serverless inference processing in the United States or Canada. Set your client's base URL to https://us-api.together.ai/v1 for the United States or https://ca-api.together.ai/v1 for Canada, using your existing API key and model IDs. There are no GPUs to provision.
New serverless models
The following models are now available on serverless : meta-models/Muse-Spark-Open-816B-A42B : 1,048,576 context length, NVFP4 quantization, function calling, and structured outputs. Pricing: $1.25 input / $4.25 output / $0.15 cached input (per 1M tokens).
New serverless models
MiniMax-M3.1-Flash is now available on the Together AI serverless platform, supporting a 1M context window, function calling, and structured outputs.