[model-inventory] Model alias inventory update - 2026-05-20

[github-actions]

Summary

The daily model inventory check has identified critical multiplier discrepancies and a missing model in the current alias and multiplier configuration.

• Providers queried: OpenAI (191 models), Anthropic (9 models), Gemini (50 models), Copilot (unavailable - reflect endpoint error)
• Total models found: 250 models across all providers
• Missing from model_multipliers.json: 145 models (mostly internal/alpha variants, embeddings, TTS, transcription)
• Stale multipliers: 27 models (deprecated/removed from APIs)
• Critical finding: Gemini 3.5 Flash is in live inventory with ET multiplier 14.0 but missing from both model_multipliers.json AND has no alias pattern

Provider Model Counts

Provider	Models Available	Status
openai	191	✅ ok
anthropic	9	✅ ok
gemini	50	✅ ok
copilot	0	⚠️ reflect endpoint unavailable

Raw API Fields Discovered

Anthropic API (/v1/models):

• ✅ max_input_tokens — context window size (200K–1M)
• ✅ max_tokens — max output tokens (32K–128K)
• ✅ capabilities.batch.supported — batch API support
• ✅ capabilities.thinking.supported — extended thinking capability
• ✅ capabilities.effort.supported — effort level control (low/medium/high/max)
• ✅ capabilities.code_execution.supported — code interpreter capability
• ✅ capabilities.image_input.supported — vision capability
• ✅ capabilities.pdf_input.supported — native PDF support

Gemini API (Google AI Studio):

• ✅ inputTokenLimit — max input tokens (1M for most models)
• ✅ outputTokenLimit — max output tokens (65K–128K)
• ✅ supportedGenerationMethods — available API methods
• ✅ thinking — extended reasoning capability (boolean)
• ✅ temperature, topP, topK, maxTemperature — generation parameters

OpenAI API (/v1/models):

• ✅ created — Unix timestamp of model release
• ✅ owned_by — owner organization (openai-internal, system, etc.)
• ⚠️ No context window, capability, or billing metadata — minimal fields available

Copilot Reflect API:

• ❌ Unavailable — reflect endpoint returned error during this run
• Would provide: vendor, capabilities.limits.max_context_window_tokens, billing.multiplier

Token Multiplier Analysis

⚠️ CRITICAL: Missing Model with Defined Multiplier

Gemini 3.5 Flash appears in:

• ✅ Copilot billing docs with ET multiplier 14.0 (New multiplier column)
• ✅ Live Gemini API inventory (gemini-3.5-flash)
• ❌ NOT in model_multipliers.json
• ❌ NOT covered by any alias pattern

Action required: Add gemini-3.5-flash to multipliers with value 14.0.

🔧 Multiplier Discrepancies (Docs vs Stored)

The following models have discrepancies between the official Copilot billing docs (New multiplier) and the stored model_multipliers.json:

Model ID	Stored Multiplier	New Multiplier	Status
gpt-5.4-nano	0.05	6.0	⚠️ 120x increase
gpt-5.4-nano-2026-03-17	0.05	6.0	⚠️ 120x increase
gpt-5.4-pro	2.0	6.0	⚠️ 3x increase
gpt-5.4-pro-2026-03-05	2.0	6.0	⚠️ 3x increase
gpt-5.2-pro	2.0	3.0	⚠️ 1.5x increase
gpt-5.2-pro-2025-12-11	2.0	3.0	⚠️ 1.5x increase
gpt-5.1-codex-mini	0.33	3.0	⚠️ 9x increase

Note: The billing docs show these as upcoming changes (New multiplier column). The stored values may reflect current production multipliers. Verify intent before updating — these could be planned changes not yet active.

📋 Missing Models (Significant Only)

The following production models are missing from model_multipliers.json:

Model ID	Provider	Inferred Multiplier	Basis
gemini-3.5-flash	gemini	14.0	Copilot billing docs
gpt-4.1-mini-2025-04-14	openai	0.1	Naming convention (-mini suffix)
gpt-4.1-nano-2025-04-14	openai	0.05	Naming convention (-nano suffix)
gpt-4o-2024-11-20	openai	0.33	Copilot billing docs
gpt-4o-2024-08-06	openai	0.33	Copilot billing docs
gpt-4o-2024-05-13	openai	0.33	Copilot billing docs
gpt-4o-mini-2024-07-18	openai	0.33	Copilot billing docs

145 total models missing — most are internal alpha/beta variants, embeddings, TTS, transcription, or vision models not used for text generation workflows.

🗑️ Stale Entries (27 models)

These models appear in model_multipliers.json but are no longer returned by any provider API:

Stale Models List

Anthropic (17 stale):

• claude-3-5-haiku, claude-3-5-opus, claude-3-5-sonnet
• claude-3-7-sonnet, claude-3-haiku, claude-3-opus, claude-3-sonnet
• claude-haiku-4-5, claude-haiku-4.5 (replaced by claude-haiku-4-5-20251001)
• claude-opus-4, claude-opus-4-1, claude-opus-4-5, claude-opus-4.5 (replaced by dated variants)
• claude-sonnet-4, claude-sonnet-4-5, claude-sonnet-4.5, claude-sonnet-4.6 (replaced by dated variants)

Gemini (5 stale):

• gemini-1.5-flash, gemini-1.5-pro (replaced by gemini-2.x series)
• gemini-2.5-computer-use-preview (replaced by gemini-2.5-computer-use-preview-10-2025)
• gemini-2.5-flash-native-audio-preview-12-2025 (not in current API)
• gemini-3.1-flash-live-preview (not in current API)

OpenAI (2 stale):

• gpt-41-copilot (internal alias, removed)
• o1-mini (replaced by o3-mini/o4-mini)

Other (3 stale):

• grok-code-fast-1, raptor-mini (removed from API)

Action: Consider marking these as deprecated for one minor version before removal per R-REG-009.

Proposed Alias Updates

1. Add Gemini 3.5 Flash Support

What: Extend gemini-flash alias to cover the new Gemini 3.5 Flash model
Why: gemini-3.5-flash is in live inventory with a premium ET multiplier (14.0), indicating it's a higher-capability Flash variant
Syntax:

{
  "gemini-flash": [
    "copilot/gemini-*flash*",
    "google/gemini-*flash*",
    "gemini/gemini-*flash*"
  ]
}

Note: The wildcard pattern *flash* already covers gemini-3.5-flash, but the alias exists in model_aliases.json. No change needed — current pattern is sufficient.

2. Consider Adding Gemini 3.5 Flash Specific Alias

What: New alias for the premium Gemini 3.5 Flash tier
Why: ET multiplier 14.0 is significantly higher than standard Flash (0.1–0.33), suggesting distinct capability/cost tier
Syntax:

{
  "gemini-flash-premium": [
    "copilot/gemini-3.5-flash*",
    "google/gemini-3.5-flash*",
    "gemini/gemini-3.5-flash*"
  ]
}

Alternative: Could be gemini-flash-3.5 or folded into an updated gemini-pro pattern if 3.5 Flash is intended as a mid-tier model.

3. Verify o4-mini Coverage

What: Ensure reasoning alias covers o4-mini variants
Why: Live inventory includes o4-mini, o4-mini-deep-research, and alpha variants
Current pattern:

{
  "reasoning": [
    "copilot/o1*",
    "copilot/o3*",
    "copilot/o4*",
    "openai/o1*",
    "openai/o3*",
    "openai/o4*"
  ]
}

Status: ✅ Already covered — o4* wildcard matches all o4-mini variants. No change needed.

4. Verify Deep Research Coverage

What: Ensure deep-research alias covers all Gemini deep research models
Why: Live inventory includes deep-research-max-preview-04-2026, deep-research-preview-04-2026, deep-research-pro-preview-12-2025
Current pattern:

{
  "deep-research": [
    "copilot/deep-research*",
    "copilot/o3-deep-research*",
    "copilot/o4-mini-deep-research*",
    "google/deep-research*",
    "gemini/deep-research*",
    "openai/o3-deep-research*",
    "openai/o4-mini-deep-research*"
  ]
}

Status: ✅ Already covered — wildcard patterns match all deep-research variants. No change needed.

Summary of Recommendations

1. CRITICAL: Add gemini-3.5-flash to model_multipliers.json with value 14.0
2. Consider: Add gemini-flash-premium alias for the 3.5 Flash tier (optional — existing gemini-flash already matches)
3. Verify: Confirm GPT-5.4 nano/pro multiplier increases are intentional before updating (currently show 120x and 3x increases from docs)
4. Deprecate: Mark 27 stale models as deprecated in next minor release

Full Model Lists by Provider

Anthropic Models (9)

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

OpenAI GPT-5/GPT-4/o-series Models (95)

gpt-4
gpt-4-0613
gpt-4-turbo
gpt-4-turbo-2024-04-09
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-4o
gpt-4o-2024-05-13
gpt-4o-2024-08-06
gpt-4o-2024-11-20
gpt-4o-mini
gpt-4o-mini-2024-07-18
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-5.1
gpt-5.1-2025-11-13
gpt-5.1-chat-latest
gpt-5.1-codex
gpt-5.1-codex-max
gpt-5.1-codex-max-customsummarizer
gpt-5.1-codex-mini
gpt-5.2
gpt-5.2-2025-12-11
gpt-5.2-chat-latest
gpt-5.2-codex
gpt-5.2-pro
gpt-5.2-pro-2025-12-11
gpt-5.3-chat-latest
gpt-5.3-codex
gpt-5.3-codex-api-preview
gpt-5.4
gpt-5.4-2026-03-05
gpt-5.4-mini
gpt-5.4-mini-2026-03-17
gpt-5.4-nano
gpt-5.4-nano-2026-03-17
gpt-5.4-pro
gpt-5.4-pro-2026-03-05
gpt-5.5
gpt-5.5-2026-04-23
gpt-5.5-pro
gpt-5.5-pro-2026-04-23
o1
o1-2024-12-17
o1-pro
o1-pro-2025-03-19
o3
o3-2025-04-16
o3-deep-research
o3-deep-research-2025-06-26
o3-mini
o3-mini-2025-01-31
o3-pro
o3-pro-2025-06-10
o4-mini
o4-mini-2025-04-16
o4-mini-deep-research
o4-mini-deep-research-2025-06-26

Gemini Models (50)

antigravity-preview-05-2026
aqa
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
gemini-2.5-flash-native-audio-preview-09-2025
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
gemini-3.1-flash-lite-preview
gemini-3.1-flash-tts-preview
gemini-3.1-pro-preview
gemini-3.1-pro-preview-customtools
gemini-3.5-flash
gemini-embedding-001
gemini-embedding-2
gemini-embedding-2-preview
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
imagen-4.0-fast-generate-001
imagen-4.0-generate-001
imagen-4.0-ultra-generate-001
lyria-3-clip-preview
lyria-3-pro-preview
nano-banana-pro-preview
veo-2.0-generate-001
veo-3.0-fast-generate-001
veo-3.0-generate-001
veo-3.1-fast-generate-preview
veo-3.1-generate-preview
veo-3.1-lite-generate-preview

Notes

• Copilot reflect endpoint unavailable: Could not fetch live Copilot model metadata during this run. The Copilot billing multipliers table was used as the authoritative source instead.
• Internal/alpha models excluded: The 145 "missing" models include many internal test variants (e.g., crest-alpha-*, willow-alpha-*, robin-alpha-*) that should not be added to multipliers unless they become production models.
• Alias coverage is comprehensive: Existing wildcard patterns (*flash*, *sonnet*, o4*, etc.) already cover most new model generations. Only gemini-3.5-flash multiplier is missing — no alias changes required.

Generated by 📦 Daily Model Inventory Checker · ● 7.1M · ◷

• expires on May 27, 2026, 12:24 AM UTC