[model-inventory] Model alias inventory update - 2026-05-12

### Summary

Daily model inventory check for 2026-05-12. The Copilot API returned HTTP 400 (not available), so only Anthropic, Gemini, and OpenAI were queried. Key findings: one multiplier entry gap (`claude-sonnet-4-6` dash-notation), several new GPT-5.x sub-version aliases proposed, and all Gemini 3.x models are already covered by existing wildcard patterns.

- Providers queried: Anthropic, Gemini, OpenAI (Copilot: HTTP 400 — skipped)
- Total models found: ~172 (Anthropic: 9, Gemini: ~55, OpenAI: ~108)
- Proposed alias changes: 6 (new GPT-5.x version-pinning aliases)
- Multiplier gaps found: 1 missing model ID + several chat-latest aliases without entries

### Provider Model Counts

| Provider | Models Available | Status |
|----------|-----------------|--------|
| anthropic | 9 | ✅ ok |
| copilot | 0 | ❌ HTTP 400 — skipped |
| gemini | ~55 | ✅ ok |
| openai | ~108 | ✅ ok |

### Raw API Fields Discovered

**Anthropic** (`/v1/models`):
- `id`, `display_name`, `created_at`, `type` — minimal metadata; no billing or capability fields in the public list endpoint

**Gemini** (`/v1beta/models`):
- `id`, `display_name`, `description`, `input_token_limit`, `output_token_limit`, `supported_generation_methods`, `version`
- Context window fully present (`input_token_limit`, `output_token_limit`)
- Capability flags via `supported_generation_methods` (generateContent, bidiGenerateContent, embedContent, predict, predictLongRunning)
- No direct billing/pricing fields; tier must be inferred from limits and model name

**OpenAI** (`/v1/models`):
- `id`, `owned_by`, `created` — minimal metadata; no token limits or billing in the list endpoint
- `owned_by` distinguishes `openai` / `openai-internal` / `system` (internal staging) models

### Token Multiplier Analysis

#### Missing from model_multipliers.json

| Model ID | Provider | Inferred Multiplier | Basis |
|----------|----------|--------------------:|-------|
| `claude-sonnet-4-6` | anthropic | 9.0 | Docs table: Claude Sonnet 4.6 new = 9; only dot-notation `claude-sonnet-4.6` is stored |
| `gpt-5.3` | openai | 6.0 | No explicit entry; `gpt-5.3-codex` is stored (6.0), base `gpt-5.3` is not |
| `gpt-5-chat-latest` | openai | 1.0 | Alias to gpt-5 family; no entry |
| `gpt-5.1-chat-latest` | openai | 3.0 | Alias to gpt-5.1; no entry |
| `gpt-5.2-chat-latest` | openai | 3.0 | Alias to gpt-5.2; no entry |
| `gpt-5.3-chat-latest` | openai | 6.0 | Alias to gpt-5.3; no entry |

#### Stale entries (no longer returned by any API)

The following are in `model_multipliers.json` but absent from all live inventories (Anthropic, Gemini, OpenAI). They may still exist in Copilot (API unavailable today), so no removals are recommended without Copilot data:

- `claude-3-haiku`, `claude-3-sonnet`, `claude-3-opus` (Claude 3 generation)
- `claude-3-5-haiku`, `claude-3-5-sonnet`, `claude-3-7-sonnet` (Claude 3.x generation)
- `claude-haiku-4-5`, `claude-haiku-4.5` (base alias variants — `claude-haiku-4-5-20251001` is live but unnormalized forms are not returned)
- `gpt-4`, `gpt-4-turbo`, `gpt-4o`, `gpt-4o-mini` — present in OpenAI live API ✅ (not stale)

#### Inferred vs stored discrepancies

All models in the docs billing table match `model_multipliers.json` with the **new multiplier** already applied. No discrepancies.

| Model (docs) | Stored | Docs new multiplier | Match? |
|---|---|---|---|
| Claude Haiku 4.5 | 0.33 | 0.33 | ✅ |
| Claude Opus 4.5 | 15.0 | 15 | ✅ |
| Claude Opus 4.6 | 27.0 | 27 | ✅ |
| Claude Opus 4.7 | 27.0 | 27 | ✅ |
| Claude Sonnet 4.5 | 6.0 | 6 | ✅ |
| Claude Sonnet 4.6 | 9.0 (dot-notation only) | 9 | ⚠️ dash-notation missing |
| Gemini 2.5 Pro | 1.0 | 1 | ✅ |
| Gemini 3 Flash | 0.33 | 0.33 | ✅ |
| Gemini 3 Pro | 6.0 | 6 | ✅ |
| Gemini 3.1 Pro | 6.0 | 6 | ✅ |
| GPT-4o | 0.33 | 0.33 | ✅ |
| GPT-4.1 | 1.0 | 1 | ✅ |
| GPT-5.1 | 3.0 | 3 | ✅ |
| GPT-5.1-Codex | 3.0 | 3 | ✅ |
| GPT-5.1-Codex-Mini | 0.33 | 0.33 | ✅ |
| GPT-5.1-Codex-Max | 3.0 | 3 | ✅ |
| GPT-5.2 | 3.0 | 3 | ✅ |
| GPT-5.2-Codex | 3.0 | 3 | ✅ |
| GPT-5.3-Codex | 6.0 | 6 | ✅ |
| GPT-5.4 | 6.0 | 6 | ✅ |
| GPT-5.4 mini | 6.0 | 6 | ✅ |
| GPT-5.5 | 7.5 | TBD | ✅ (stored as 7.5) |
| Grok Code Fast 1 | 0.33 | 0.33 | ✅ |
| Raptor mini | 0.33 | 0.33 | ✅ |

### Proposed Alias Updates

#### 1. Fix `claude-sonnet-4-6` multiplier gap

**What**: Add dash-notation ID to `model_multipliers.json`  
**Why**: Live Anthropic API returns `claude-sonnet-4-6` (dashes) but only `claude-sonnet-4.6` (dot) is stored. Workflows using this model ID will fall back to the default multiplier.

This is a `model_multipliers.json` fix, not an alias change:
```json
"claude-sonnet-4-6": 9.0
```

#### 2. Add `gpt-5.1` through `gpt-5.5` version-pinning aliases

**What**: New aliases in `model_aliases.json` for GPT-5 sub-generations  
**Why**: OpenAI live API has `gpt-5.1`, `gpt-5.2`, `gpt-5.3`, `gpt-5.4`, `gpt-5.5` as distinct model generations with distinct multipliers (3→3→6→6→7.5). The current `gpt-5` alias uses `gpt-5*` which resolves to whichever version comes first alphabetically, making version targeting impossible for workflow authors.

```json
{
  "gpt-5.1": ["copilot/gpt-5.1*", "openai/gpt-5.1*"],
  "gpt-5.2": ["copilot/gpt-5.2*", "openai/gpt-5.2*"],
  "gpt-5.3": ["copilot/gpt-5.3*", "openai/gpt-5.3*"],
  "gpt-5.4": ["copilot/gpt-5.4*", "openai/gpt-5.4*"],
  "gpt-5.5": ["copilot/gpt-5.5*", "openai/gpt-5.5*"]
}
```

#### 3. Add `gemini-3-flash` and `gemini-3.1-flash` explicit aliases

**What**: Explicit aliases for Gemini 3 Flash and 3.1 Flash families  
**Why**: Both are live in the Gemini API. They are technically covered by the `gemini-flash` wildcard (`gemini-*flash*`) but an explicit alias gives workflow authors a stable, intention-revealing name.

```json
{
  "gemini-3-flash": ["copilot/gemini-3*flash*", "google/gemini-3*flash*", "gemini/gemini-3*flash*"],
  "gemini-3.1-flash": ["copilot/gemini-3.1*flash*", "google/gemini-3.1*flash*", "gemini/gemini-3.1*flash*"],
  "gemini-3-pro": ["copilot/gemini-3*pro*", "google/gemini-3*pro*", "gemini/gemini-3*pro*"],
  "gemini-3.1-pro": ["copilot/gemini-3.1*pro*", "google/gemini-3.1*pro*", "gemini/gemini-3.1*pro*"]
}
```

<details>
<summary><b>Full Model Lists by Provider</b></summary>

**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 (selected text-generation models)**
- 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-native-audio-preview-12-2025, 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-live-preview, gemini-3.1-flash-tts-preview, gemini-3.1-pro-preview
- gemini-3.1-pro-preview-customtools, 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

**OpenAI (key text/reasoning models)**
- gpt-4, gpt-4-0613, gpt-4-turbo, gpt-4-turbo-2024-04-09, gpt-4o, gpt-4o-mini
- 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-5.1, gpt-5.1-2025-11-13, gpt-5.1-chat-latest, gpt-5.1-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini
- gpt-5.2, gpt-5.2-2025-12-11, gpt-5.2-chat-latest, gpt-5.2-codex, gpt-5.2-pro
- gpt-5.3-chat-latest, gpt-5.3-codex
- gpt-5.4, gpt-5.4-2026-03-05, gpt-5.4-mini, gpt-5.4-nano, gpt-5.4-pro
- gpt-5.5, gpt-5.5-2026-04-23, gpt-5.5-pro
- 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
- o4-mini, o4-mini-2025-04-16, o4-mini-deep-research, o4-mini-deep-research-2025-06-26

</details>

### Notes

- Copilot API returned HTTP 400 — multiplier and alias analysis is based on Anthropic/Gemini/OpenAI direct APIs and the official GitHub Copilot billing docs table only. Re-run when Copilot API is available.
- Many OpenAI models in the live list are internal alpha/staging variants (e.g., `crest-alpha-*`, `glacier-alpha-*`, `willow-alpha-*`) — these are excluded from alias and multiplier considerations.
- Gemini 4 Gemma models (`gemma-4-26b-a4b-it`, `gemma-4-31b-it`) are already covered by `gemini/gemma*` in the `gemma` alias.
- Gemini 3.x models are already covered by the `gemini-flash`/`gemini-pro` wildcard aliases; the proposed Gemini 3 explicit aliases are optional quality-of-life improvements.







> Generated by [Daily Model Inventory Checker](https://github.com/github/gh-aw/actions/runs/25704992041/agentic_workflow) · ● 21.2M · [◷](https://github.com/search?q=repo%3Agithub%2Fgh-aw+is%3Aissue+%22gh-aw-workflow-call-id%3A+github%2Fgh-aw%2Fdaily-model-inventory%22&type=issues)
> - [x] expires  on May 19, 2026, 12:19 AM UTC

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[model-inventory] Model alias inventory update - 2026-05-12 #31609

Summary

Provider Model Counts

Raw API Fields Discovered

Token Multiplier Analysis

Missing from model_multipliers.json

Stale entries (no longer returned by any API)

Inferred vs stored discrepancies

Proposed Alias Updates

1. Fix `claude-sonnet-4-6` multiplier gap

2. Add `gpt-5.1` through `gpt-5.5` version-pinning aliases

3. Add `gemini-3-flash` and `gemini-3.1-flash` explicit aliases

Notes

Metadata

Assignees

Labels

Type

Fields

Projects

Milestone

Relationships

Development

Provider	Models Available	Status
anthropic	9	✅ ok
copilot	0	❌ HTTP 400 — skipped
gemini	~55	✅ ok
openai	~108	✅ ok

Model ID	Provider	Inferred Multiplier	Basis
`claude-sonnet-4-6`	anthropic	9.0	Docs table: Claude Sonnet 4.6 new = 9; only dot-notation `claude-sonnet-4.6` is stored
`gpt-5.3`	openai	6.0	No explicit entry; `gpt-5.3-codex` is stored (6.0), base `gpt-5.3` is not
`gpt-5-chat-latest`	openai	1.0	Alias to gpt-5 family; no entry
`gpt-5.1-chat-latest`	openai	3.0	Alias to gpt-5.1; no entry
`gpt-5.2-chat-latest`	openai	3.0	Alias to gpt-5.2; no entry
`gpt-5.3-chat-latest`	openai	6.0	Alias to gpt-5.3; no entry

Model (docs)	Stored	Docs new multiplier	Match?
Claude Haiku 4.5	0.33	0.33	✅
Claude Opus 4.5	15.0	15	✅
Claude Opus 4.6	27.0	27	✅
Claude Opus 4.7	27.0	27	✅
Claude Sonnet 4.5	6.0	6	✅
Claude Sonnet 4.6	9.0 (dot-notation only)	9	⚠️ dash-notation missing
Gemini 2.5 Pro	1.0	1	✅
Gemini 3 Flash	0.33	0.33	✅
Gemini 3 Pro	6.0	6	✅
Gemini 3.1 Pro	6.0	6	✅
GPT-4o	0.33	0.33	✅
GPT-4.1	1.0	1	✅
GPT-5.1	3.0	3	✅
GPT-5.1-Codex	3.0	3	✅
GPT-5.1-Codex-Mini	0.33	0.33	✅
GPT-5.1-Codex-Max	3.0	3	✅
GPT-5.2	3.0	3	✅
GPT-5.2-Codex	3.0	3	✅
GPT-5.3-Codex	6.0	6	✅
GPT-5.4	6.0	6	✅
GPT-5.4 mini	6.0	6	✅
GPT-5.5	7.5	TBD	✅ (stored as 7.5)
Grok Code Fast 1	0.33	0.33	✅
Raptor mini	0.33	0.33	✅

[model-inventory] Model alias inventory update - 2026-05-12 #31609

Description

Summary

Provider Model Counts

Raw API Fields Discovered

Token Multiplier Analysis

Missing from model_multipliers.json

Stale entries (no longer returned by any API)

Inferred vs stored discrepancies

Proposed Alias Updates

1. Fix claude-sonnet-4-6 multiplier gap

2. Add gpt-5.1 through gpt-5.5 version-pinning aliases

3. Add gemini-3-flash and gemini-3.1-flash explicit aliases

Notes

Metadata

Metadata

Assignees

Labels

Type

Fields

Projects

Milestone

Relationships

Development

Issue actions

1. Fix `claude-sonnet-4-6` multiplier gap

2. Add `gpt-5.1` through `gpt-5.5` version-pinning aliases

3. Add `gemini-3-flash` and `gemini-3.1-flash` explicit aliases