Skip to content

Conversation

@ammar-agent
Copy link
Collaborator

Change OpenAI service_tier default from auto to priority for low-latency responses.

Changes

  • Default to priority service tier for faster responses
  • Support all OpenAI service tiers: auto, default, flex, priority
  • Allow override via providers.jsonc

Usage

Users can configure in ~/.mux/providers.jsonc:

{
  "openai": {
    "apiKey": "sk-...",
    "serviceTier": "flex"
  }
}

Service tier options:

  • priority: Low-latency responses (new default)
  • flex: 50% cheaper, higher latency (o3, o4-mini, gpt-5)
  • auto/default: Standard processing

Generated with mux

…roviders.jsonc

- Change default from 'auto' to 'priority' for low-latency responses
- Support all OpenAI service tiers: auto, default, flex, priority
- Read serviceTier from providers.jsonc config and pass through to API

Users can override in ~/.mux/providers.jsonc:
{
  "openai": {
    "apiKey": "sk-...",
    "serviceTier": "flex"  // 50% cheaper, higher latency
  }
}

_Generated with mux_
@ammario ammario merged commit c150c30 into main Dec 12, 2025
33 of 35 checks passed
@ammario ammario deleted the openai-service-tier branch December 12, 2025 04:42
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