From 684ac65d9f6ffe326f9ca973b5d58970b43a861a Mon Sep 17 00:00:00 2001 From: "cursor[bot]" Date: Wed, 8 Jul 2026 06:06:29 +0000 Subject: [PATCH] Sync together-dedicated-endpoints with mintlify-docs#927 Document Together AI's new provisioned throughput inference tier as a routing option for stock-model production workloads: - Add a Hand-Off bullet in SKILL.md so agents point users running a stock model in production and wanting a defined throughput/reliability SLA (without managing hardware) to provisioned throughput (contact sales), and clarify that dedicated endpoints remain the right fit for fine-tuned/uploaded models or when the user needs direct control over hardware, latency, and throughput. --- skills/together-dedicated-endpoints/SKILL.md | 1 + 1 file changed, 1 insertion(+) diff --git a/skills/together-dedicated-endpoints/SKILL.md b/skills/together-dedicated-endpoints/SKILL.md index 41518d3..22115f2 100644 --- a/skills/together-dedicated-endpoints/SKILL.md +++ b/skills/together-dedicated-endpoints/SKILL.md @@ -29,6 +29,7 @@ Typical fits: - Use `together-chat-completions` for serverless chat inference - Use `together-dedicated-containers` for custom runtimes or nonstandard inference pipelines - Use `together-gpu-clusters` for raw infrastructure or cluster orchestration +- For production **stock-model** workloads that need a defined SLA (committed throughput and reliability) without managing hardware, point users to Together's [provisioned throughput](https://docs.together.ai/docs/inference/provisioned-throughput) tier (reserved PTU capacity, one-month minimum, contact sales). Use dedicated endpoints instead when the user needs to serve a fine-tuned or uploaded model, or wants direct control over hardware, latency, and throughput. ## Quick Routing