From cf6a4a5d66d3872e74afd5a8f3e4b38c2d2f860b Mon Sep 17 00:00:00 2001 From: "cursor[bot]" Date: Wed, 8 Jul 2026 06:05:28 +0000 Subject: [PATCH] Sync together-chat-completions with mintlify-docs#927 Document Together AI's new provisioned throughput inference tier: - Add hand-off note in SKILL.md so agents route production stock-model workloads that need a defined throughput/reliability SLA to provisioned throughput (contact sales) instead of dedicated endpoints. - Update the rate-limits best-practices in references/api-parameters.md to list provisioned throughput alongside dedicated endpoints for strict capacity or SLA needs. --- skills/together-chat-completions/SKILL.md | 1 + skills/together-chat-completions/references/api-parameters.md | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/skills/together-chat-completions/SKILL.md b/skills/together-chat-completions/SKILL.md index a636ab5..0d117fb 100644 --- a/skills/together-chat-completions/SKILL.md +++ b/skills/together-chat-completions/SKILL.md @@ -35,6 +35,7 @@ clearly offline batch processing, vector retrieval, model training, or infrastru - Use `together-fine-tuning` when the user wants to train or adapt a model - Use `together-dedicated-endpoints` when the user needs always-on single-tenant hosting - Use `together-dedicated-containers` or `together-gpu-clusters` for custom infrastructure +- 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 term, contact sales; uses the same chat/completions API surface) ## Quick Routing diff --git a/skills/together-chat-completions/references/api-parameters.md b/skills/together-chat-completions/references/api-parameters.md index ff2e06c..ccf3e96 100644 --- a/skills/together-chat-completions/references/api-parameters.md +++ b/skills/together-chat-completions/references/api-parameters.md @@ -389,7 +389,7 @@ Best practices: - plan against the latest headers instead of a hard-coded RPM table - keep traffic steady instead of bursty - use batch inference for high-volume offline jobs -- use dedicated endpoints for strict capacity or SLA requirements +- for strict capacity or SLA requirements, use provisioned throughput (reserved capacity on supported stock models with a defined throughput and reliability SLA, contact sales) or dedicated endpoints (single-tenant GPUs, self-serve) ## Debug Mode