# モデル図鑑 📖 AIチーム用モデルカタログ

> 最終更新: 2026-09-29T12:22:35Z | 掲載数: 14 | 最終確認: 2026-09-28 | データ正本: `catalog/models.yaml`

正本は YAML。この Markdown は一覧用の生成物。値の追加・修正は正本を直して再生成する。

## 📊 サマリ

| 指標 | 値 |
| --- | --- |
| 掲載モデル | 14 |
| active | 13 |
| preview | 1 |
| deprecated | 0 |
| 最終確認日 | 2026-09-28 |

## 🏢 提供元サマリ

| 提供元 | 掲載 | active | preview | その他 |
| --- | --- | --- | --- | --- |
| anthropic | 4 | 4 | 0 | 0 |
| openai | 6 | 6 | 0 | 0 |
| google | 2 | 1 | 1 | 0 |
| xai | 2 | 2 | 0 | 0 |

## 🧭 えらび帖

Quest の種類ごとのおすすめ（モデル・設定・理由）。正本は `catalog/erabi.md`。この節は生成物。

> 更新日: 2026-09-29 📣 前回からのニュース - 仮サンプル（ホシゾラ-9 / コガタ-2 / メガネ-1）を止めて、図鑑本番の推薦に切り替えた - 図鑑の最終確認は 2026-09-28。掲載 14機種

### 🟡 かんがえ中 ── 設計・バグ発見

- おすすめ: カニ様 × Claude Opus 5.5
- 設定: high ／ context：1000000（一度に読める量） ／ fast：不明 ／ 使う場所：Claude Code（純正）／T3
- 理由: 長い設計と知識仕事が得意。Fable 5.1 に近い仕事を、より安いコストでやる、と図鑑にある。公式も Opus 5 からこっちへ。 🥈 代打：エビ様 × ChatGPT 6 Astra ／ 設定：high ／ context：1050000 ／ fast：不明 ── いちばん難しい推論・調査・コーディング向け。速い。コストは特高。 ⚠️ T3の表示名は未確認（カニ様 / Opus 5.5）

### 🟢 おまかせ ── 実装・修正

- おすすめ: カニ様 × Claude Sonnet 5
- 設定: high ／ context：1000000 ／ fast：不明 ／ 使う場所：Claude Code（純正）／T3（表示名: Claude Sonnet 5）
- 理由: 速さと賢さのバランスが売り。実装とツール利用が得意。コスト中、速め。T3の席も確認済み。 🥈 代打：エビ様 × ChatGPT 6 Sol ／ 設定：medium ／ context：1050000 ／ fast：不明 ── 複雑なコーディングとエージェント作業向け。公式も「賢さとコストのバランス」はこっち。速い。コスト中。 ⚠️ T3の Context Window 既定は 200k。代打の Sol は T3表示名が未確認

### 🎨 えり好み ── デザイン

- おすすめ: カイ様 × Gemini 3.1 Pro
- 設定: high ／ context：1048576 ／ fast：不明 ／ 使う場所：Antigravity／Gemini アプリ／T3
- 理由: 図鑑に「マルチモーダル」とある。見た目の話をするときの土台。デザイン専用とは書いてないから、たぶん。 🥈 代打：カニ様 × Claude Opus 5.5 ／ 設定：medium ／ context：1000000 ／ fast：不明 ── 知識仕事が得意。スライドや資料は Fable 5.1 の得意だけどサブスク外。近いのはこっち。たぶん。 ⚠️ 3.1 Pro は preview。T3の表示名は未確認

### 👓 PRレビュー ── 目を通す

- おすすめ: かーくん × Grok 4.7
- 設定: high ／ context：500000 ／ fast：不明 ／ 使う場所：Cursor／T3／Grok Build
- 理由: 図鑑に「より強い自己チェック」とある。難しい長めの仕事も得意。公式はコードとチャットの推奨を 4.6 から 4.7 に切っている。 🥈 代打：カニ様 × Claude Opus 5.5 ／ 設定：high ／ context：1000000 ／ fast：不明 ── 長いコーディングの検証は Opus 家の得意（Opus 5 の記述）。後継の 5.5 を使う。 ⚠️ T3の表示名は未確認（かーくん / ウニ様 の Grok 4.7）

### 🧪 今回のおためし

- おすすめ: エビ様 × ChatGPT 6 Sol
- 設定: medium ／ context：1050000 ／ fast：不明 ／ 使う場所：Codex（純正）／T3
- 理由: 公式のバランス枠なのに、T3の表示名が未確認。おまかせの代打を、一回本番で回してみる。 ⚠️ T3の表示名は未確認

## 📋 全モデル一覧

| # | モデル | 提供元 | 状態 | API ID | コンテキスト | Effort | コスト | 速度 | コーディング | T3 | 確認日 |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | Claude Opus 5 | anthropic | active | `claude-opus-5` | 1,000,000 | low / medium / high / xhigh / max（既定: high） | 高 | 普通 | strong | カニ様（未確認） | 2026-09-28 |
| 2 | Claude Opus 5.5 | anthropic | active | `claude-opus-5-5` | 1,000,000 | low / medium / high / xhigh / max（既定: medium） | 高 | 普通 | strong | カニ様（未確認） | 2026-09-28 |
| 3 | Claude Sonnet 5 | anthropic | active | `claude-sonnet-5` | 1,000,000 | low / medium / high / xhigh / max（既定: high） | 中 | 速め | strong | カニ様: Claude Sonnet 5 | 2026-09-24 |
| 4 | Claude Fable 5.1 | anthropic | active | `claude-fable-5-1` | 1,000,000 | low / medium / high / xhigh / max（既定: high） | 特高 | 遅め | strong | カニ様（未確認） | 2026-09-24 |
| 5 | ChatGPT 5.6 Sol | openai | active | `gpt-5.6-sol` | 1,050,000 | none / low / medium / high / xhigh / max（既定: medium） | 高 | 速め | strong | エビ様（未確認） | 2026-09-24 |
| 6 | ChatGPT 5.6 Terra | openai | active | `gpt-5.6-terra` | 1,050,000 | none / low / medium / high / xhigh / max（既定: medium） | 中 | 速め | strong | エビ様（未確認） | 2026-09-28 |
| 7 | ChatGPT 5.6 Luna | openai | active | `gpt-5.6-luna` | 1,050,000 | none / low / medium / high / xhigh / max（既定: medium） | 低 | 速め | unknown | エビ様（未確認） | 2026-09-28 |
| 8 | ChatGPT 6 Astra | openai | active | `gpt-6-astra` | 1,050,000 | low / medium / high / xhigh / max（既定: unknown） | 特高 | 速め | strong | エビ様: GPT-6-Astra | 2026-09-28 |
| 9 | ChatGPT 6 Sol | openai | active | `gpt-6-sol` | 1,050,000 | none / low / medium / high / xhigh / max（既定: medium） | 中 | 速め | strong | エビ様（未確認） | 2026-09-28 |
| 10 | ChatGPT 6 Luna | openai | active | `gpt-6-luna` | 1,050,000 | none / low / medium / high / xhigh / max（既定: medium） | 低 | 速め | unknown | エビ様（未確認） | 2026-09-28 |
| 11 | Gemini 3.8 Flash | google | active | `gemini-3.8-flash` | 1,048,576 | low / medium / high（既定: medium） | 低 | unknown | strong | カイ様: Gemini 3.8 Flash (High), Gemini 3.8 Flash (Medium), Gemini 3.8 Flash (Low) | 2026-09-24 |
| 12 | Gemini 3.1 Pro | google | preview | `gemini-3.1-pro-preview` | 1,048,576 | low / medium / high（既定: high） | 中 | unknown | strong | カイ様（未確認） | 2026-09-24 |
| 13 | Grok 4.6 | xai | active | `grok-4.6` | 500,000 | low / medium / high / xhigh（既定: high） | 中 | unknown | strong | かーくん: Cursor Grok 4.6 / ウニ様: Grok Build | 2026-09-24 |
| 14 | Grok 4.7 | xai | active | `grok-4.7` | 500,000 | low / medium / high / xhigh（既定: high） | 中 | unknown | strong | かーくん（未確認） / ウニ様（未確認） | 2026-09-24 |

## 🎛️ T3code 対応

| エージェント | モデル | ラベル | 既定ラベル | メニュー |
| --- | --- | --- | --- | --- |
| カニ様 | Claude Opus 5 | unknown | unknown | - |
| カニ様 | Claude Opus 5.5 | unknown | unknown | - |
| カニ様 | Claude Sonnet 5 | Claude Sonnet 5 | Claude Sonnet 5 | Reasoning: Low / Medium / High / Extra High / Max / Ultrathink（既定: High）; Context Window: 200k / 1M（既定: 200k） |
| カニ様 | Claude Fable 5.1 | unknown | unknown | - |
| エビ様 | ChatGPT 5.6 Sol | unknown | unknown | - |
| エビ様 | ChatGPT 5.6 Terra | unknown | unknown | - |
| エビ様 | ChatGPT 5.6 Luna | unknown | unknown | - |
| エビ様 | ChatGPT 6 Astra | GPT-6-Astra | GPT-6-Astra | Reasoning: Low / Medium / High / Extra High / Max / Ultra（既定: Medium）; Service Tier: Standard / Fast（既定: Standard） |
| エビ様 | ChatGPT 6 Sol | unknown | unknown | - |
| エビ様 | ChatGPT 6 Luna | unknown | unknown | - |
| カイ様 | Gemini 3.8 Flash | Gemini 3.8 Flash (High) / Gemini 3.8 Flash (Medium) / Gemini 3.8 Flash (Low) | Gemini 3.8 Flash (High) | - |
| カイ様 | Gemini 3.1 Pro | unknown | unknown | - |
| かーくん | Grok 4.6 | Cursor Grok 4.6 | Cursor Grok 4.6 | Effort: Low / Medium / High / Extra High（既定: High）; Fast: On / Off（既定: unknown） |
| ウニ様 | Grok 4.6 | Grok Build | Grok Build | - |
| かーくん | Grok 4.7 | unknown | unknown | - |
| ウニ様 | Grok 4.7 | unknown | unknown | - |

## 📝 モデル詳細

### Claude Opus 5

`claude-opus-5`

| 項目 | 値 |
| --- | --- |
| display_name | Claude Opus 5 |
| provider | anthropic |
| api_id | `claude-opus-5` |
| status | active |
| thinking | high |
| coding | strong |
| tool_use | yes |
| context_max | 1,000,000 |
| effort_levels | low / medium / high / xhigh / max |
| effort_default | high |
| cost_class | 高 |
| speed_class | 普通 |
| harnesses | Claude.ai / Claude API / Claude Code |
| first_seen | 2026-07-24 |
| last_verified | 2026-09-28 |

**得意**

Complex agentic coding and enterprise work; strong verification/iteration on long coding tasks (Anthropic models overview + Opus 5 launch)

**T3**

カニ様（未確認）

**eri_feel**

（まだなし）

**根拠**

- https://platform.claude.com/docs/en/models/opus-5/overview
- https://platform.claude.com/docs/en/about-claude/pricing
- https://platform.claude.com/docs/en/build-with-claude/effort
- https://www.anthropic.com/news/claude-opus-5
- https://code.claude.com/docs/en/model-config

**メモ**

Active (legacy); Anthropic recommends migrating to Opus 5.5. Adaptive thinking; API effort default high. Pricing $5/$25 per MTok. Comparative latency Moderate → speed_class 普通. Output $25 → cost_class 高. Claude Code Anthropic API opus alias resolved to Opus 5 through v2.1.279; from v2.1.280+ opus (and account defaults on Anthropic API) → Opus 5.5. T3 labels/menus unknown (eri 2026-09-17).

### Claude Opus 5.5

`claude-opus-5-5`

| 項目 | 値 |
| --- | --- |
| display_name | Claude Opus 5.5 |
| provider | anthropic |
| api_id | `claude-opus-5-5` |
| status | active |
| thinking | high |
| coding | strong |
| tool_use | yes |
| context_max | 1,000,000 |
| effort_levels | low / medium / high / xhigh / max |
| effort_default | medium |
| cost_class | 高 |
| speed_class | 普通 |
| harnesses | Claude.ai / Claude API / Claude Code |
| first_seen | 2026-09-22 |
| last_verified | 2026-09-28 |

**得意**

Long-running agentic coding and knowledge work; first Claude 5.5 Opus; performs near Fable 5.1 on most work at lower cost (Anthropic Opus 5.5 announcement + overview)

**T3**

カニ様（未確認）

**eri_feel**

（まだなし）

**根拠**

- https://platform.claude.com/docs/en/models/opus-5-5/overview
- https://www.anthropic.com/claude-opus-5-5
- https://platform.claude.com/docs/en/about-claude/pricing
- https://platform.claude.com/docs/en/build-with-claude/effort
- https://code.claude.com/docs/en/model-config

**メモ**

Adaptive thinking always on. API effort default medium (unlike Opus 5 high). All five effort levels. Pricing $4/$20 per MTok. Comparative latency Moderate → speed_class 普通. Output $20 → cost_class 高. Released 2026-09-22. Status Active (latest). Max output 128K. Claude Code Anthropic API: opus alias + Pro/Max/Team/Enterprise/API defaults → Opus 5.5 (v2.1.280+; was Opus 5 before). T3 labels/menus unknown (not yet confirmed by eri).

### Claude Sonnet 5

`claude-sonnet-5`

| 項目 | 値 |
| --- | --- |
| display_name | Claude Sonnet 5 |
| provider | anthropic |
| api_id | `claude-sonnet-5` |
| status | active |
| thinking | high |
| coding | strong |
| tool_use | yes |
| context_max | 1,000,000 |
| effort_levels | low / medium / high / xhigh / max |
| effort_default | high |
| cost_class | 中 |
| speed_class | 速め |
| harnesses | Claude.ai / Claude API / Claude Code |
| first_seen | 2026-06-30 |
| last_verified | 2026-09-24 |

**得意**

Best speed/intelligence mix; agentic coding, tool use, and knowledge work at Sonnet price (Anthropic models overview + Sonnet 5 launch)

**T3**

カニ様: Claude Sonnet 5

- カニ様 / Reasoning: Low / Medium / High / Extra High / Max / Ultrathink（既定: High）
- カニ様 / Context Window: 200k / 1M（既定: 200k）

**eri_feel**

（まだなし）

**根拠**

- https://platform.claude.com/docs/en/models/sonnet-5/overview
- https://platform.claude.com/docs/en/about-claude/pricing
- https://platform.claude.com/docs/en/build-with-claude/effort
- https://www.anthropic.com/news/claude-sonnet-5
- https://code.claude.com/docs/en/model-config
- T3code confirmed by eri 2026-09-17

**メモ**

Adaptive thinking; API effort default high. Pricing $2/$10 per MTok. Comparative latency Fast → speed_class 速め. Output $10 → cost_class 中. Claude Code Anthropic API sonnet alias → Sonnet 5 (v2.1.197+). T3 menus use eri-confirmed spellings (Extra High / Ultrathink), not normalized to official xhigh.

### Claude Fable 5.1

`claude-fable-5-1`

| 項目 | 値 |
| --- | --- |
| display_name | Claude Fable 5.1 |
| provider | anthropic |
| api_id | `claude-fable-5-1` |
| status | active |
| thinking | high |
| coding | strong |
| tool_use | yes |
| context_max | 1,000,000 |
| effort_levels | low / medium / high / xhigh / max |
| effort_default | high |
| cost_class | 特高 |
| speed_class | 遅め |
| harnesses | Claude.ai / Claude API / Claude Code |
| first_seen | 2026-09-01 |
| last_verified | 2026-09-24 |

**得意**

Demanding reasoning and long-horizon agentic work; stronger long-running agentic coding, multistep research, and document/spreadsheet/slide work (Anthropic Fable 5.1 overview)

**T3**

カニ様（未確認）

**eri_feel**

（まだなし）

**根拠**

- https://platform.claude.com/docs/en/models/fable-5-1/overview
- https://platform.claude.com/docs/en/about-claude/pricing
- https://platform.claude.com/docs/en/build-with-claude/effort

**メモ**

Adaptive thinking always on; API effort default high; all five effort levels. Pricing $10/$50 per MTok. Comparative latency Slower → speed_class 遅め. Output $50 → cost_class 特高. Released 2026-09-01. Max output 128K. T3 labels/menus unknown (eri 2026-09-17).

### ChatGPT 5.6 Sol

`chatgpt-5-6-sol`

| 項目 | 値 |
| --- | --- |
| display_name | ChatGPT 5.6 Sol |
| provider | openai |
| api_id | `gpt-5.6-sol` |
| status | active |
| thinking | high |
| coding | strong |
| tool_use | yes |
| context_max | 1,050,000 |
| effort_levels | none / low / medium / high / xhigh / max |
| effort_default | medium |
| cost_class | 高 |
| speed_class | 速め |
| harnesses | ChatGPT / Codex / OpenAI API |
| first_seen | 2026-07-09 |
| last_verified | 2026-09-24 |

**得意**

GPT-5.6 flagship for complex professional work; coding, knowledge work, computer use (OpenAI models + GPT-5.6 post)

**T3**

エビ様（未確認）

**eri_feel**

（まだなし）

**根拠**

- https://developers.openai.com/api/docs/models/gpt-5.6-sol
- https://developers.openai.com/api/docs/models
- https://openai.com/index/gpt-5-6/
- https://developers.openai.com/api/docs/guides/reasoning

**メモ**

Alias gpt-5.6 → Sol. Seed catalog id chatgpt-5-6-sol kept. reasoning.effort none|low|medium|high|xhigh|max; default medium. Pricing $4/$20 per MTok (promo through at least 2026-11-21). Model page latency badge Fast → speed_class 速め. Output $20 → cost_class 高. Function calling yes. Distinct from GPT-6 Sol (gpt-6-sol). T3 labels/menus unknown (eri 2026-09-17).

### ChatGPT 5.6 Terra

`chatgpt-5-6-terra`

| 項目 | 値 |
| --- | --- |
| display_name | ChatGPT 5.6 Terra |
| provider | openai |
| api_id | `gpt-5.6-terra` |
| status | active |
| thinking | high |
| coding | strong |
| tool_use | yes |
| context_max | 1,050,000 |
| effort_levels | none / low / medium / high / xhigh / max |
| effort_default | medium |
| cost_class | 中 |
| speed_class | 速め |
| harnesses | ChatGPT / Codex / OpenAI API |
| first_seen | - |
| last_verified | 2026-09-28 |

**得意**

Balances intelligence and cost; roughly the mini tier of the GPT-5.6 family (OpenAI GPT-5.6 Terra model page)

**T3**

エビ様（未確認）

**eri_feel**

（まだなし）

**根拠**

- https://developers.openai.com/api/docs/models/gpt-5.6-terra
- https://developers.openai.com/api/docs/models
- https://developers.openai.com/api/docs/pricing

**メモ**

Official Fast latency badge → speed_class 速め. Pricing $2/$12 per MTok (short context); output $12 → cost_class 中. Long-context output $18 would be 高 — used short-context base. Function calling yes. reasoning.effort none|low|medium|high|xhigh|max; default medium. Models overview Choosing a model now points balance/cost defaults to GPT-6 Sol/Luna; GPT-5.6 Terra remains active. T3 labels/menus unknown (not in eri 2026-09-17 screen notes).

### ChatGPT 5.6 Luna

`chatgpt-5-6-luna`

| 項目 | 値 |
| --- | --- |
| display_name | ChatGPT 5.6 Luna |
| provider | openai |
| api_id | `gpt-5.6-luna` |
| status | active |
| thinking | medium |
| coding | unknown |
| tool_use | yes |
| context_max | 1,050,000 |
| effort_levels | none / low / medium / high / xhigh / max |
| effort_default | medium |
| cost_class | 低 |
| speed_class | 速め |
| harnesses | ChatGPT / Codex / OpenAI API |
| first_seen | - |
| last_verified | 2026-09-28 |

**得意**

Cost-sensitive high-volume workloads; roughly the nano tier of the GPT-5.6 family (OpenAI GPT-5.6 Luna model page)

**T3**

エビ様（未確認）

**eri_feel**

（まだなし）

**根拠**

- https://developers.openai.com/api/docs/models/gpt-5.6-luna
- https://developers.openai.com/api/docs/models
- https://developers.openai.com/api/docs/pricing

**メモ**

Official Fast latency badge → speed_class 速め. Pricing $0.20/$1.20 per MTok (short context); output $1.20 → cost_class 低. Function calling yes. reasoning.effort none|low|medium|high|xhigh|max; default medium. coding left unknown (no official coding-strength label on model page). Distinct from GPT-6 Luna (gpt-6-luna). Models overview Choosing a model now points cost-sensitive defaults to GPT-6 Luna; GPT-5.6 Luna remains active. T3 labels/menus unknown (not in eri 2026-09-17 screen notes).

### ChatGPT 6 Astra

`chatgpt-6-astra`

| 項目 | 値 |
| --- | --- |
| display_name | ChatGPT 6 Astra |
| provider | openai |
| api_id | `gpt-6-astra` |
| status | active |
| thinking | high |
| coding | strong |
| tool_use | yes |
| context_max | 1,050,000 |
| effort_levels | low / medium / high / xhigh / max |
| effort_default | unknown |
| cost_class | 特高 |
| speed_class | 速め |
| harnesses | ChatGPT / Codex / OpenAI API |
| first_seen | - |
| last_verified | 2026-09-28 |

**得意**

Most capable OpenAI model for hardest end-to-end reasoning, coding, computer use, research (OpenAI models + GPT-6 Astra page)

**T3**

エビ様: GPT-6-Astra

- エビ様 / Reasoning: Low / Medium / High / Extra High / Max / Ultra（既定: Medium）
- エビ様 / Service Tier: Standard / Fast（既定: Standard）

**eri_feel**

（まだなし）

**根拠**

- https://developers.openai.com/api/docs/models/gpt-6-astra
- https://developers.openai.com/api/docs/models
- https://openai.com/index/gpt-6-astra/
- https://developers.openai.com/api/docs/guides/reasoning
- T3code confirmed by eri 2026-09-17

**メモ**

Seed catalog id chatgpt-6-astra kept. reasoning.effort low|medium|high|xhigh|max (none unsupported). Official model page does not state API default effort → effort_default unknown (T3 Reasoning default Medium is UI-only). Pricing $10/$50 per MTok; Fast mode 2x price. Model page latency badge Fast → speed_class 速め (verified 2026-09-28). Output $50 → cost_class 特高. Function calling yes. first_seen empty pending authoritative launch-day stamp. T3 menus use eri-confirmed spellings (Extra High / Ultra).

### ChatGPT 6 Sol

`chatgpt-6-sol`

| 項目 | 値 |
| --- | --- |
| display_name | ChatGPT 6 Sol |
| provider | openai |
| api_id | `gpt-6-sol` |
| status | active |
| thinking | high |
| coding | strong |
| tool_use | yes |
| context_max | 1,050,000 |
| effort_levels | none / low / medium / high / xhigh / max |
| effort_default | medium |
| cost_class | 中 |
| speed_class | 速め |
| harnesses | ChatGPT / Codex / OpenAI API |
| first_seen | 2026-09-22 |
| last_verified | 2026-09-28 |

**得意**

Built for complex coding and agentic workflows; GPT-6 mid-tier balancing intelligence and cost (OpenAI GPT-6 Sol model page + models overview)

**T3**

エビ様（未確認）

**eri_feel**

（まだなし）

**根拠**

- https://developers.openai.com/api/docs/models/gpt-6-sol
- https://developers.openai.com/api/docs/models
- https://developers.openai.com/api/docs/guides/reasoning

**メモ**

Distinct from GPT-5.6 Sol (gpt-5.6-sol). reasoning.effort none|low|medium|high|xhigh|max; default medium. Pricing $2/$10 per MTok. Model page latency badge Fast → speed_class 速め. Output $10 → cost_class 中. Function calling yes. Announced 2026-09-22. OpenAI models overview Choosing a model now recommends GPT-6 Sol to balance intelligence and cost (was GPT-5.6 Terra in earlier guidance). T3 labels/menus unknown (not yet confirmed by eri).

### ChatGPT 6 Luna

`chatgpt-6-luna`

| 項目 | 値 |
| --- | --- |
| display_name | ChatGPT 6 Luna |
| provider | openai |
| api_id | `gpt-6-luna` |
| status | active |
| thinking | medium |
| coding | unknown |
| tool_use | yes |
| context_max | 1,050,000 |
| effort_levels | none / low / medium / high / xhigh / max |
| effort_default | medium |
| cost_class | 低 |
| speed_class | 速め |
| harnesses | ChatGPT / Codex / OpenAI API |
| first_seen | 2026-09-22 |
| last_verified | 2026-09-28 |

**得意**

Most efficient GPT-6 model for focused, high-volume tasks (OpenAI GPT-6 Luna model page + models overview)

**T3**

エビ様（未確認）

**eri_feel**

（まだなし）

**根拠**

- https://developers.openai.com/api/docs/models/gpt-6-luna
- https://developers.openai.com/api/docs/models
- https://developers.openai.com/api/docs/guides/reasoning

**メモ**

Distinct from GPT-5.6 Luna (gpt-5.6-luna). reasoning.effort none|low|medium|high|xhigh|max; default medium. Pricing $0.10/$0.50 per MTok; output $0.50 → cost_class 低. Model page latency badge Fast → speed_class 速め (verified 2026-09-28). OpenAI models overview now recommends GPT-6 Luna for cost-sensitive high-volume workloads (alongside GPT-6 Sol for balance). Function calling yes. coding left unknown (efficiency/high-volume wording, no coding-strength label). Announced 2026-09-22. T3 labels/menus unknown (not yet confirmed by eri).

### Gemini 3.8 Flash

`gemini-3-8-flash`

| 項目 | 値 |
| --- | --- |
| display_name | Gemini 3.8 Flash |
| provider | google |
| api_id | `gemini-3.8-flash` |
| status | active |
| thinking | high |
| coding | strong |
| tool_use | yes |
| context_max | 1,048,576 |
| effort_levels | low / medium / high |
| effort_default | medium |
| cost_class | 低 |
| speed_class | unknown |
| harnesses | Gemini app / Gemini API |
| first_seen | - |
| last_verified | 2026-09-24 |

**得意**

Most intelligent Flash: long-horizon software engineering, autonomous agents, complex enterprise workflows (Gemini 3.8 Flash model page)

**T3**

カイ様: Gemini 3.8 Flash (High), Gemini 3.8 Flash (Medium), Gemini 3.8 Flash (Low)

**eri_feel**

（まだなし）

**根拠**

- https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash
- https://ai.google.dev/gemini-api/docs/generate-content/latest-model
- https://ai.google.dev/gemini-api/docs/pricing
- https://ai.google.dev/gemini-api/docs/thinking
- T3code confirmed by eri 2026-09-17

**メモ**

thinking_level low|medium|high; default medium (minimal unsupported). Intro pricing $0.75/$3.75 per MTok through 2026-12-31 → output $3.75 cost_class 低. No Anthropic-style comparative latency label on model page → speed_class unknown (Flash marketing speed wording not treated as comparative latency enum). Function calling yes. T3: three labels by effort variant; menus none; default High label.

### Gemini 3.1 Pro

`gemini-3-1-pro`

| 項目 | 値 |
| --- | --- |
| display_name | Gemini 3.1 Pro |
| provider | google |
| api_id | `gemini-3.1-pro-preview` |
| status | preview |
| thinking | high |
| coding | strong |
| tool_use | yes |
| context_max | 1,048,576 |
| effort_levels | low / medium / high |
| effort_default | high |
| cost_class | 中 |
| speed_class | unknown |
| harnesses | Gemini app / Gemini API |
| first_seen | 2026-02-19 |
| last_verified | 2026-09-24 |

**得意**

Advanced reasoning/multimodal Pro; optimized for software engineering and precise tool-using agentic workflows (Gemini 3.1 Pro preview page)

**T3**

カイ様（未確認）

**eri_feel**

（まだなし）

**根拠**

- https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview
- https://ai.google.dev/gemini-api/docs/pricing
- https://ai.google.dev/gemini-api/docs/thinking
- https://cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-1-pro

**メモ**

Public endpoint gemini-3.1-pro-preview; status=preview. thinking_level low|medium|high; default high. Pricing $2/$12 per MTok (<=200k); $4/$18 (>200k). cost_class 中 from standard <=200k output $12 (note: >200k output $18 would be 高). speed_class unknown. Function calling + thinking yes. T3: Legacy models has High and Low two entries; exact labels unknown (eri 2026-09-17).

### Grok 4.6

`grok-4-6`

| 項目 | 値 |
| --- | --- |
| display_name | Grok 4.6 |
| provider | xai |
| api_id | `grok-4.6` |
| status | active |
| thinking | high |
| coding | strong |
| tool_use | yes |
| context_max | 500,000 |
| effort_levels | low / medium / high / xhigh |
| effort_default | high |
| cost_class | 中 |
| speed_class | unknown |
| harnesses | Grok / Grok Build / Cursor / xAI API |
| first_seen | - |
| last_verified | 2026-09-24 |

**得意**

Frontier coding, agentic tasks, and knowledge work; long-running agents (xAI Grok 4.6 docs + news)

**T3**

かーくん: Cursor Grok 4.6 / ウニ様: Grok Build

- かーくん / Effort: Low / Medium / High / Extra High（既定: High）
- かーくん / Fast: On / Off（既定: unknown）

**eri_feel**

（まだなし）

**根拠**

- https://docs.x.ai/developers/models/grok-4.6
- https://docs.x.ai/developers/models
- https://docs.x.ai/developers/pricing
- https://x.ai/news/grok-4-6
- T3code confirmed by eri 2026-09-17
- T3 ウニ様=Grok Build by eri 2026-09-20

**メモ**

reasoning_effort low|medium|high|xhigh; default high. Pricing $2/$6 per MTok (<200k); $4/$12 (>=200k). cost_class 中 from base output $6. No official comparative-latency enum → speed_class unknown (per eri: reset from 速め). Function calling yes. T3 Fast choices quoted On/Off; Fast default unknown. T3 Effort uses Extra High (not xhigh). T3: ウニ様=Grok Build を eri 追記。Grok Build 側 Effort/Fast メニューは未確認のため空。Successor Grok 4.7 now recommended for code/chat (xAI models docs).

### Grok 4.7

`grok-4-7`

| 項目 | 値 |
| --- | --- |
| display_name | Grok 4.7 |
| provider | xai |
| api_id | `grok-4.7` |
| status | active |
| thinking | high |
| coding | strong |
| tool_use | yes |
| context_max | 500,000 |
| effort_levels | low / medium / high / xhigh |
| effort_default | high |
| cost_class | 中 |
| speed_class | unknown |
| harnesses | Grok / Grok Build / Cursor / xAI API |
| first_seen | 2026-09-21 |
| last_verified | 2026-09-24 |

**得意**

Frontier coding, agentic tasks, and knowledge work; longer difficult tasks and stronger self-checks; xAI recommended model for code and chat (xAI Grok 4.7 docs + news)

**T3**

かーくん（未確認） / ウニ様（未確認）

**eri_feel**

（まだなし）

**根拠**

- https://docs.x.ai/developers/models/grok-4.7
- https://docs.x.ai/developers/models
- https://docs.x.ai/developers/pricing
- https://x.ai/news/grok-4-7

**メモ**

reasoning_effort low|medium|high|xhigh; default high. Pricing $2/$6 per MTok (<200k); $4/$12 (>=200k) — same as Grok 4.6. cost_class 中 from base output $6. No official comparative-latency enum → speed_class unknown. Function calling yes. Announced 2026-09-21. Fast variant 2x speed / 2x price mentioned in news. T3 labels/menus unknown (not yet confirmed by eri).

---

生成: `2026-09-29T12:22:35Z` / 正本: `catalog/models.yaml` / 生成コマンド: `python3 scripts/build_catalog.py`