Skip to content

Document the flex service tier#19

Open
sopwg612 wants to merge 3 commits into
mainfrom
flex-service-tier-docs
Open

Document the flex service tier#19
sopwg612 wants to merge 3 commits into
mainfrom
flex-service-tier-docs

Conversation

@sopwg612

@sopwg612 sopwg612 commented Jul 9, 2026

Copy link
Copy Markdown
Contributor

What

Splits the chat/overview.mdx Service tier section into Priority and Flex subsections.

  • Flex: service_tier: "flex" → 20% discount, standard scheduling, best-effort (may be queued or return 429 under load); positioned for retryable, latency-tolerant work.
  • Adds Python / JavaScript / cURL examples for flex.
  • Generalizes the service_tier parameter-table row and the fallback note to cover both tiers.
  • Keeps the #service-tier anchor (deep-linked from the model pricing table in the web app).

Related

  • deepinfra/backend#3471 — exposes the flex rate in the API.
  • deepinfra/web#476 — the flex web UI.

🤖 Generated with Claude Code

https://claude.ai/code/session_013pg5hqXmjMK99hggVC6UF9

sopwg612 and others added 3 commits July 9, 2026 22:33
Split the Service Tier section into Priority and Flex subsections. Flex:
service_tier="flex", 20% discount, standard scheduling, best-effort
(may be queued or 429'd under load). Adds Python/JS/cURL examples and
generalizes the parameter row and fallback note to both tiers. Keeps the
#service-tier anchor used by the model pricing table.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013pg5hqXmjMK99hggVC6UF9
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013pg5hqXmjMK99hggVC6UF9
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_013pg5hqXmjMK99hggVC6UF9
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants