DX-596-together-chat-completions: sync with mintlify-docs#927#37
Merged
zainhas merged 1 commit intoJul 10, 2026
Merged
Conversation
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.
blainekasten
approved these changes
Jul 10, 2026
zainhas
deleted the
docs-sync/together-chat-completions/mintlify-docs-pr-927
branch
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Syncs
together-chat-completionswith togethercomputer/mintlify-docs#927 "DX-641: Document provisioned throughput", which introduces Together AI's new provisioned throughput inference tier (reserved PTU capacity for supported stock models with a defined throughput and reliability SLA, one-month minimum term, sales-only).Changed docs that triggered this sync
docs/inference/overview.mdx— reframes inference options as three tiers (serverless, provisioned throughput, dedicated endpoints) and notes all three share the same inference API surface.docs/inference/pricing.mdx— adds a Provisioned throughput pricing section ($0.05 per PTU per minute, one-month minimum, model-specific token-to-PTU conversion ratios).docs/serverless/rate-limits.mdx— adds provisioned throughput to the list of options for workloads that need higher throughput or a defined SLA.Skill changes
SKILL.md— Add a Hand Off note so agents route production stock-model workloads that need a defined throughput/reliability SLA (without managing hardware) to Together's provisioned throughput tier (contact sales) rather than dedicated endpoints.references/api-parameters.md— Update the Rate Limits & Build Tiers best-practices bullet to list provisioned throughput alongside dedicated endpoints as options for strict capacity or SLA requirements, and note the trade-off (PT = reserved PTU capacity on stock models via sales contract; dedicated = single-tenant GPUs, self-serve).Generated by the Sync Skills Cursor Automation. Please review before merging.