homelab-infra/apps/codex-proxy/config/models.yaml

# Codex model catalog
#
# Sources:
#   1. Static (below) — Codex-specific models (not returned by /backend-api/models)
#   2. Dynamic          — general ChatGPT models fetched from /backend-api/codex/models
#
# Dynamic fetch merges with static; backend entries win for shared IDs.
# Models endpoint now requires ?client_version= query parameter.
#
# Last updated: 2026-05-08 (Codex runtime context metadata)

models:
  # ── GPT-5.5 (newest general-purpose, Plus-only) ─────────────────────
  - id: gpt-5.5
    displayName: GPT-5.5
    description: Latest general-purpose flagship
    isDefault: false
    supportedReasoningEfforts:
      - { reasoningEffort: low,    description: "Fast responses with lighter reasoning" }
      - { reasoningEffort: medium, description: "Balances speed and reasoning depth" }
      - { reasoningEffort: high,   description: "Greater reasoning depth for complex problems" }
      - { reasoningEffort: xhigh,  description: "Extra high reasoning depth" }
    defaultReasoningEffort: medium
    inputModalities: [text, image]
    outputModalities: [text]
    contextWindow: 272000
    maxContextWindow: 272000
    maxOutputTokens: 128000
    truncationPolicyLimit: 10000
    supportsPersonality: false
    upgrade: null

  # ── GPT-5.4 family (default flagship) ───────────────────────────────
  - id: gpt-5.4
    displayName: GPT-5.4
    description: Latest frontier agentic coding model
    isDefault: true
    supportedReasoningEfforts:
      - { reasoningEffort: low,    description: "Fast responses with lighter reasoning" }
      - { reasoningEffort: medium, description: "Balances speed and reasoning depth" }
      - { reasoningEffort: high,   description: "Greater reasoning depth for complex problems" }
      - { reasoningEffort: xhigh,  description: "Extra high reasoning depth" }
    defaultReasoningEffort: medium
    inputModalities: [text, image]
    outputModalities: [text]
    contextWindow: 272000
    maxContextWindow: 1000000
    maxOutputTokens: 128000
    truncationPolicyLimit: 10000
    supportsPersonality: false
    upgrade: null

  - id: gpt-5.4-mini
    displayName: GPT-5.4 Mini
    description: Smaller frontier agentic coding model
    isDefault: false
    supportedReasoningEfforts:
      - { reasoningEffort: low,    description: "Fast responses with lighter reasoning" }
      - { reasoningEffort: medium, description: "Balances speed and reasoning depth" }
      - { reasoningEffort: high,   description: "Greater reasoning depth for complex problems" }
      - { reasoningEffort: xhigh,  description: "Extra high reasoning depth" }
    defaultReasoningEffort: medium
    inputModalities: [text, image]
    outputModalities: [text]
    contextWindow: 400000
    maxOutputTokens: 128000
    supportsPersonality: false
    upgrade: null

  # ── GPT-5.3 Codex ──────────────────────────────────────────────────
  - id: gpt-5.3-codex
    displayName: GPT-5.3 Codex
    description: Frontier Codex-optimized agentic coding model
    isDefault: false
    supportedReasoningEfforts:
      - { reasoningEffort: low,    description: "Fast responses with lighter reasoning" }
      - { reasoningEffort: medium, description: "Balances speed and reasoning depth" }
      - { reasoningEffort: high,   description: "Greater reasoning depth for complex problems" }
      - { reasoningEffort: xhigh,  description: "Extra high reasoning depth" }
    defaultReasoningEffort: medium
    inputModalities: [text, image]
    contextWindow: 400000
    maxOutputTokens: 128000
    supportsPersonality: false
    upgrade: null

  # ── GPT-5.2 (general-purpose) ────────────────────────────────────────
  - id: gpt-5.2
    displayName: GPT-5.2
    description: Optimized for professional work and long-running agents
    isDefault: false
    supportedReasoningEfforts:
      - { reasoningEffort: low,    description: "Balances speed with some reasoning" }
      - { reasoningEffort: medium, description: "Solid balance of reasoning depth and latency" }
      - { reasoningEffort: high,   description: "Maximizes reasoning depth" }
      - { reasoningEffort: xhigh,  description: "Extra high reasoning" }
    defaultReasoningEffort: medium
    inputModalities: [text, image]
    contextWindow: 400000
    maxOutputTokens: 128000
    supportsPersonality: true
    upgrade: null

  # ── GPT-5 Codex family ──────────────────────────────────────────────
  - id: gpt-5-codex
    displayName: GPT-5 Codex
    description: GPT-5 Codex
    isDefault: false
    supportedReasoningEfforts:
      - { reasoningEffort: low,    description: "Fastest responses" }
      - { reasoningEffort: medium, description: "Balanced speed and quality" }
      - { reasoningEffort: high,   description: "Deepest reasoning" }
    defaultReasoningEffort: medium
    inputModalities: [text, image]
    contextWindow: 400000
    maxOutputTokens: 128000
    supportsPersonality: false
    upgrade: null

  # No exact official token-limit page found for id gpt-5-codex-mini on 2026-05-08.
  - id: gpt-5-codex-mini
    displayName: GPT-5 Codex Mini
    description: GPT-5 Codex Mini — lightweight
    isDefault: false
    supportedReasoningEfforts:
      - { reasoningEffort: medium, description: "Balanced" }
      - { reasoningEffort: high,   description: "Greater reasoning" }
    defaultReasoningEffort: medium
    inputModalities: [text]
    supportsPersonality: false
    upgrade: null

  # ── Image generation (tool-invoked, not a chat model) ───────────────
  - id: gpt-image-2
    displayName: GPT Image 2
    description: Image generation backend invoked via the image_generation tool (not a chat model)
    isDefault: false
    supportedReasoningEfforts: []
    defaultReasoningEffort: medium
    inputModalities: [text, image]
    outputModalities: [image]
    supportsPersonality: false
    upgrade: null

  # ── Open-source models ──────────────────────────────────────────────
  - id: gpt-oss-120b
    displayName: GPT-OSS 120B
    description: Open-source 120B model
    isDefault: false
    supportedReasoningEfforts:
      - { reasoningEffort: low,    description: "Fastest responses" }
      - { reasoningEffort: medium, description: "Balanced" }
      - { reasoningEffort: high,   description: "Deepest reasoning" }
    defaultReasoningEffort: medium
    inputModalities: [text]
    contextWindow: 131072
    supportsPersonality: false
    upgrade: null

  - id: gpt-oss-20b
    displayName: GPT-OSS 20B
    description: Open-source 20B model
    isDefault: false
    supportedReasoningEfforts:
      - { reasoningEffort: low,    description: "Fastest responses" }
      - { reasoningEffort: medium, description: "Balanced" }
      - { reasoningEffort: high,   description: "Deepest reasoning" }
    defaultReasoningEffort: medium
    inputModalities: [text]
    contextWindow: 131072
    supportsPersonality: false
    upgrade: null

# User-editable aliases. Claude Desktop can expose Claude-shaped model names
# while this gateway maps them to Codex model IDs internally.
aliases:
  claude-opus-4-7: gpt-5.5
  claude-sonnet-4-6: gpt-5.4
  claude-haiku-4-5: gpt-5.3-codex