[model-inventory] Model alias inventory update - 2026-05-19

[github-actions]

Summary

Daily model alias inventory check for 2026-05-19. All existing alias patterns and multipliers are well-aligned with live APIs. One minor alias gap found (raptor-mini has no alias coverage). Two production OpenAI models missing from model_multipliers.json. Copilot reflect data was unavailable (no configured endpoint).

• Providers queried: OpenAI, Anthropic, Gemini (Copilot: unavailable)
• Total models found: 249 (openai: 190, gemini: 50, anthropic: 9)
• Proposed alias changes: 1 (add raptor-mini pattern to mini alias)
• Multiplier gaps found: 2 production models missing from model_multipliers.json

Provider Model Counts

Provider	Models Available	Status
openai	190	✅ ok
anthropic	9	✅ ok
gemini	50	✅ ok
copilot	N/A	⚠️ unavailable (no configured endpoint in reflect.json)

Raw API Fields Discovered

Anthropic: id, display_name, created_at, type — no billing or context-limit fields exposed via the models API.

Gemini: Rich metadata — inputTokenLimit, outputTokenLimit, supportedGenerationMethods, temperature, topP, topK, thinking (boolean, present on Gemini 3.x Pro models). The thinking: true flag is useful for identifying reasoning-capable models. No billing multiplier fields.

OpenAI: id, created (unix timestamp), owned_by — minimal metadata. No context-limit or billing fields in the models list endpoint. Alpha/internal models account for ~60% of the returned list.

Token Multiplier Analysis

Missing from model_multipliers.json

Model ID	Provider	Inferred Multiplier	Basis
gpt-5-search-api	openai	~1.0	Production search model; similar tier to gpt-5 (1.0); not in billing docs table
gpt-5-search-api-2025-10-14	openai	~1.0	Versioned form of above
gpt-5-chat-latest	openai	~1.0	Rolling latest pointer, mirrors gpt-5 (1.0)

Note: nano-banana-pro-preview (Gemini) is an internal alias for gemini-3-pro-image-preview (confirmed by displayName: "Nano Banana Pro" and description: "Gemini 3 Pro Image Preview" in raw API). The latter is already in model_multipliers.json at 6.0. No action needed.

Stale entries (no longer returned by any API)

The following are absent from all three live APIs but remain in model_multipliers.json. Most are Copilot-specific models or short-form aliases kept for backward compatibility — no removal recommended:

• grok-code-fast-1 — XAI model, not in OpenAI/Anthropic/Gemini APIs; likely Copilot-specific
• raptor-mini — Copilot-specific (confirmed in GitHub billing docs at 0.33×)
• gpt-41-copilot — Copilot-specific variant
• Claude 3.x legacy entries (claude-3-5-haiku, claude-3-5-sonnet, claude-3-haiku, etc.) — legacy kept for backward compat
• Short-form dot-notation aliases (claude-haiku-4.5, claude-opus-4.5, claude-sonnet-4.6, etc.) — convenience aliases

Inferred vs stored discrepancies

All models in the official GitHub billing docs table match the stored multipliers exactly. No discrepancies found.

Model	Docs New Multiplier	Stored	Status
Claude Haiku 4.5	0.33	0.33	✅ match
Claude Sonnet 4.5	6	6.0	✅ match
Claude Sonnet 4.6	9	9.0	✅ match
Claude Opus 4.5	15	15.0	✅ match
Claude Opus 4.6	27	27.0	✅ match
Claude Opus 4.7	27	27.0	✅ match
Gemini 2.5 Pro	1	1.0	✅ match
Gemini 3 Flash	0.33	0.33	✅ match
Gemini 3 Pro	6	6.0	✅ match
Gemini 3.1 Pro	6	6.0	✅ match
GPT-4.1	1	1.0	✅ match
GPT-5.1	3	3.0	✅ match
GPT-5.2	3	3.0	✅ match
GPT-5.3-Codex	6	6.0	✅ match
GPT-5.4	6	6.0	✅ match
GPT-5.4 mini	6	6.0	✅ match
GPT-5.5	TBD	7.5	i️ new multiplier not yet set; current stored value retained
Raptor mini	0.33	0.33	✅ match

Proposed Alias Updates

1. Add raptor-mini to mini alias

What: Add copilot/raptor*mini* pattern to the mini alias.

Why: raptor-mini is listed in the official GitHub Copilot billing docs at 0.33× (same tier as gpt-5-mini, gemini-3-flash), is already in model_multipliers.json, but has no alias pattern allowing workflow authors to reference it via mini or small.

Syntax:

{
  "mini": ["haiku", "gpt-5-mini", "gpt-5-nano", "gemini-flash-lite", "copilot/raptor*mini*"]
}

Notes

• All 18 models in the official GitHub billing docs multiplier table are correctly represented in model_multipliers.json.
• The Gemini API returns several non-chat models (imagen, veo, lyria, robotics, embedding) — these are intentionally excluded from multipliers.
• OpenAI API returns ~100 internal/alpha models (crest-, willow-, robin-*, etc.) — these are pre-production and not tracked in multipliers.
• The deep-research alias covers both Gemini and OpenAI deep-research model variants correctly.
• Gemini 3.x thinking models (thinking: true flag) are covered by existing gemini-pro and gemini-flash aliases.
• Copilot reflect data was unavailable this run; Copilot-specific models (raptor-mini, grok-code-fast-1, gpt-41-copilot) were validated against the billing docs table instead.

Full Model Lists by Provider

Anthropic (9 models)

• claude-haiku-4-5-20251001
• claude-opus-4-1-20250805
• claude-opus-4-20250514
• claude-opus-4-5-20251101
• claude-opus-4-6
• claude-opus-4-7
• claude-sonnet-4-20250514
• claude-sonnet-4-5-20250929
• claude-sonnet-4-6

Gemini (50 models — key chat/generation models)

• deep-research-max-preview-04-2026
• deep-research-preview-04-2026
• deep-research-pro-preview-12-2025
• gemini-2.0-flash, gemini-2.0-flash-001
• gemini-2.0-flash-lite, gemini-2.0-flash-lite-001
• gemini-2.5-computer-use-preview-10-2025
• gemini-2.5-flash, gemini-2.5-flash-image, gemini-2.5-flash-lite
• gemini-2.5-flash-native-audio-latest/preview variants
• gemini-2.5-flash-preview-tts, gemini-2.5-pro, gemini-2.5-pro-preview-tts
• gemini-3-flash-preview, gemini-3-pro-image-preview, gemini-3-pro-preview
• gemini-3.1-flash-image-preview, gemini-3.1-flash-lite/preview, gemini-3.1-flash-live-preview
• gemini-3.1-flash-tts-preview, gemini-3.1-pro-preview, gemini-3.1-pro-preview-customtools
• gemini-flash-latest, gemini-flash-lite-latest, gemini-pro-latest
• gemini-robotics-er-1.5-preview, gemini-robotics-er-1.6-preview
• gemma-4-26b-a4b-it, gemma-4-31b-it
• nano-banana-pro-preview (alias for gemini-3-pro-image-preview)
• (plus embedding, imagen, veo, lyria non-chat models)

OpenAI (190 models — production models)

• gpt-4, gpt-4-0613, gpt-4-turbo, gpt-4-turbo-2024-04-09
• gpt-4o, gpt-4o-2024-05-13/08-06/11-20, gpt-4o-mini, gpt-4o-mini-2024-07-18
• gpt-4.1, gpt-4.1-2025-04-14, gpt-4.1-mini, gpt-4.1-mini-2025-04-14, gpt-4.1-nano, gpt-4.1-nano-2025-04-14
• gpt-5, gpt-5-2025-08-07, gpt-5-chat-latest, gpt-5-codex, gpt-5-mini, gpt-5-mini-2025-08-07
• gpt-5-nano, gpt-5-nano-2025-08-07, gpt-5-pro, gpt-5-pro-2025-10-06
• gpt-5-search-api, gpt-5-search-api-2025-10-14
• gpt-5.1 through gpt-5.5 families (chat-latest, codex, mini, pro, nano variants)
• o1, o1-2024-12-17, o1-pro, o1-pro-2025-03-19
• o3, o3-2025-04-16, o3-mini, o3-mini-2025-01-31, o3-pro, o3-pro-2025-06-10
• o3-deep-research, o3-deep-research-2025-06-26
• o4-mini, o4-mini-2025-04-16, o4-mini-deep-research, o4-mini-deep-research-2025-06-26
• (plus ~100 alpha/internal/non-chat models)

Generated by 📦 Daily Model Inventory Checker · ● 5.3M · ◷

• expires on May 26, 2026, 12:22 AM UTC