Releasesby IbisNew serverless models
Update8 days agoUnverifiedAdded Oct 17, 2026
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).
Topics: Pricing
More Together AI platform releases
Every Together AI platform releaseNew 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
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).
Post-training
Post-training lets you write your own training loop and run it against Together AI GPUs. Your code builds each batch and chooses the loss function and learning rate, while the GPUs you provision run the forward and backward passes, optimizer steps, and sampling. It bills per GPU-minute.
What's included:
- Three training methods: Supervised fine-tuning (SFT) , direct preference optimization (DPO) , and reinforcement learning with group relative policy optimization (GRPO) . Each method trains a low-rank adapter (LoRA) or the full model weights. Custom loss functions : Train with any objective you compute in PyTorch from the model's log-probabilities.
New serverless models
The following models are now available on serverless : MiniMaxAI/MiniMax-M3.1-Flash : 1,048,576 context length, NVFP4 quantization, function calling, and structured outputs. Pricing: $0.15 input / $0.60 output / $0.015 cached input (per 1M tokens).
New provisioned throughput models
The following models are now available on provisioned throughput : zai-org/GLM-5.3 . zai-org/GLM-5.3-Flash . deepseek-ai/DeepSeek-V4.1-Flash .
Dynamic rate limits for serverless retired
Serverless no longer applies dynamic rate limits that scale with your recent traffic. Most users will no longer encounter rate limits, though requests can still be limited during periods of high demand. If you get a 429 Too Many Requests response, reduce your request rate and spread out bursts.
Together Link beta
Together Link runs six coding agents on models hosted by Together AI: Claude Code, Codex, OpenCode, and Pi Code in the terminal, plus Claude Desktop (including Cowork) and ChatGPT Desktop. Install it with one command, launch your agent through it, and your normal agent configuration stays untouched. It's now in beta on macOS and Linux.
Also shipped on Oct 16, 2026
Together AI in October 20262026.10.08
Make a voice you already have speak another language or accent, with the same speaker. Call POST /voice-generator/localize on a flagship or custom voice, pick an accent, and get candidates back in seconds to audition and convert like Voice Design candidates. GET /voice-generator/available-accents lists the accents you can target.
Neon Realtime in public beta, new AI Gateway models, Stripe real-time sync, CJK search in Lakebase Search, and more release - Oct 16, 2026
Neon Realtime is in public beta. Neon now has realtime, built by the team behind Electric. Neon Realtime turns any SQL query into a live query. Subscribe to it ...
TypeSafe AI Jev 1.14.0 is now available on Unity Gateway
TypeSafe AI Jev 1.14.0 is now available on Unity Gateway. TypeSafe AI hosts it, and an account admin must enable the Externally-hosted TypeSafe AI Models preview. TypeSafe's terms govern its use.
Gemini Enterprise: Configure citations for custom MCP data stores
You can configure the citation_mappings parameter for custom Model Context Protocol (MCP) data stores using the REST API to display source citation chips when Gemini Enterprise answers questions using tools on your custom MCP server. This feature is generally available (GA). For more information, see Configure citations for custom MCP data stores .
[In preview] Public Preview: Azure Databricks Private network gateway
Private network gateway for Azure Databricks is now in Public Preview, enabling serverless compute to connect to resources in your virtual network (VNet) and transitively connected networks through a single managed gateway. Customers can use the gateway t
Cloud Agent Canvases and Environment Improvements
Canvases from cloud agents Cloud agents can now build interactive canvases as part of their work. Share a finished canvas with your team by sending its link. Learn more about sharing canvases . Environments API The Environments API is now available in beta. Use it to programmatically create and manage the cloud environments your agents run in.