
Gemini API の Genie 4:1秒あたり0.10ドル、通話を終了するまで課金
- OrcaNEWOrcaCyber: Hy4 Flash Abliterated / Uncensored2026-11-18$0.07 / $0.28 100万トークンあたり · 187 tok/s
- tencentNEWTencent: Hy4 Flash2026-11-16$0.02 / $0.07 100万トークンあたり · 413 tok/s
- GoogleNEWGoogle: Gemini 4 Carbon2026-11-10$2.00 / $10.00 100万トークンあたり · 87 tok/s
- AnthropicNEWAnthropic: Claude Fable 5.22026-11-09$8.00 / $40.00 100万トークンあたり · 119 tok/s
- orcaNEWOrca: OrcaC2 1.02026-11-079 tok/s
- OrcaOrcaCyber: GLM 5.3 Abliterated / Uncensored2026-11-04$3.00 / $5.00 100万トークンあたり · 89 tok/s
- OrcaOrcaCyber: Hy4 Abliterated / Uncensored2026-11-04$0.80 / $1.60 100万トークンあたり · 135 tok/s
- OrcaOrcaCyber: Kimi K3.1 Pro Abliterated / Uncensored2026-11-04$2.00 / $5.00 100万トークンあたり · 78 tok/s
- tencentTencent: Hy42026-11-04$0.83 / $2.50 100万トークンあたり · 116 tok/s
- OrcaOrcaCyber: MiniMax M3.1 Flash Abliterated / Uncensored2026-10-29$0.80 / $1.60 100万トークンあたり · 114 tok/s
- OrcaOrcaCyber: GLM 5.3 Flash Abliterated / Uncensored2026-10-27$0.80 / $1.60 100万トークンあたり · 66 tok/s
- OrcaOrcaCyber: Qwen3.8 Flash Next Abliterated / Uncensored2026-10-26$0.80 / $1.60 100万トークンあたり · 91 tok/s
- OrcaOrcaCyber: MiMo V2.6 Flash Abliterated / Uncensored2026-10-26$0.80 / $1.60 100万トークンあたり · 41 tok/s
- MoonshotMoonshotAI: Kimi K3.1 Pro2026-10-2447知能
- OrcaOrcaCyber: DeepSeek V4.1 Flash Abliterated / Uncensored2026-10-23$0.80 / $1.60 100万トークンあたり · 212 tok/s
- minimaxMiniMax: M3.1 Flash2026-10-1929知能
- OrcaOrca: OrcaCyber Ultra 1.02026-10-17$5.00 / $10.00 100万トークンあたり · 111 tok/s
- deepseekDeepSeek: DeepSeek V4.1 Flash 10172026-10-1733知能
- DeepSeekDeepSeek: DeepSeek V4.1 Flash 09102026-10-17$0.15 / $0.60 100万トークンあたり · 168 tok/s
- DeepSeekDeepSeek: DeepSeek V4.1 Flash2026-10-1740知能
The detail that decides whether Genie 4 is a toy or a line item is not the 720p picture. It is that Google bills the model by the second of streamed output and keeps billing until your code tells it to stop. Genie 4 reached the Gemini API on November 19, 2026, one day after it went live inside Project Genie for Google AI Ultra subscribers, and on the same day Project Genie invitations started reaching Google AI Pro members who had joined the waitlist. That pricing model — roughly $0.10 per second, no free tier, no caching, no batch discounts — is the part worth reading carefully before anyone puts a world model behind a product surface. The comparison everyone will make is against Gemini Omni 1.2 Flash, Google's offline video model at about $0.07 per second of 720p; the two look close on a rate card and behave nothing alike in a build.
3つの日付、そのうちローンチは1つだけ
Genie 4 has been announced three times in three weeks, which is why the coverage of it keeps talking past itself. Google DeepMind published the research announcement on October 27, 2026, with access limited to trusted testers and a public waitlist. On November 18 it began rolling the model out inside Project Genie to eligible Google AI Ultra subscribers, alongside upgrades to Genie 3 and a community gallery. On November 19 it opened the door developers actually care about: models/genie-4 on the Gemini API, through the Interactions API and Google AI Studio.
The fourth event is the one in the signal: on the evening of November 19, TestingCatalog posted a screenshot of an invitation telling a Google AI Pro member they were off the Project Genie waitlist and now had access "as part of your Google AI Pro subscription." That is a user report, not a Google announcement, and at the time of writing the Project Genie page still reads "available at launch for eligible Google AI Ultra subscribers. Google AI Pro members can join the waitlist." But waitlist invitations going out in volume is how a staged rollout widens, and it is the difference between a $99.99 subscription and a $19.99 one for the consumer half of this product.
What none of those four events changed: the model. Same weights, same session cap, same limitations Google published in October and again in the November model card.
世界の本当の価格、毎秒
Genie 4 is priced as video tokens rather than as a request. Google's rate card lists $1.50 per million input tokens for text and reference images, $9.00 per million output text tokens, and $17.50 per million output video tokens with the 48 kHz stereo audio bundled in. Because the model emits 240 video tokens per frame at 24 frames per second — 5,760 tokens a second — that works out to roughly $0.10 per second of streamed world, or about $6.05 a minute. These are Google's published numbers, not an independent measurement; nobody outside Google has published a metered bill to check them against.
The arithmetic that matters is what a session can cost. Google caps a session at 120 seconds, and says visual coherence and object permanence are strongest during the first 45 to 90 seconds. So the useful part of a session is $4.50 to $9.00, and the ceiling on one uninterrupted session is about $12.00. That is cheap for a pre-visualization pass and expensive for anything that runs while a user is idle.
The billing mechanics are where a prototype turns into an incident. Google's own documentation warns that exiting a local block or closing a browser tab detaches the transport without stopping server-side generation. The only things that stop the meter are complete() or cancel(); detachment does not, and Genie 4 has no session resumption, so a dropped socket cannot be resumed and still costs you until the session ends. Google's prompt guide notes that AI Studio itself pauses a stream when the tab is hidden for more than 10 seconds, precisely so idle tabs do not burn paid video tokens. Your client has to do that job yourself.

実際に呼び出すとどう見えるか
Genie 4 is not a generateContent model and it is not on the Live API. It runs on the Interactions API, which Google has described as generally available since June 2026 and as the place new models and capabilities launch. The endpoint accepts models/genie-4 or the bare genie-4, requires api_version v1beta, and requires a paid-tier API key — the free tier is listed as not available.
接続モデルが珍しい点であり、それが構築できるものを左右します:
• トランスポート — ブラウザには WebRTC(video 要素と JSON 制御イベント用の SCTP データチャネル)を、Python と Node には WebSocket を使用します。WebSocket は base64 JPEG フレームと、自身でデコードする 48 kHz 16-bit ステレオ PCM を配信します。
• セッショントークン — サーバーがインタラクションを作成し、単一セッション用の認証トークンを発行し、クライアントにはそのトークンだけが渡されます。APIキーがブラウザに届くことは決してなく、これはこの設計の中で文句なしに優れている唯一の部分です。
• イベント — world_setup イベントは、テキスト、WebRTC 上の 48 KB 未満の 16:9 参照画像、またはその両方からワールドをシードします; user_action は、WASD と 4 つの矢印キー用のネイティブ key_down/key_up を伝達します;セッション中は input イベントが、ストリームの実行中に天気、オブジェクト、またはイベントを変更するテキストを伝達します。
• Startup cost — first frame arrives roughly 5 to 9 seconds after the world prompt, per Google's integration guide. That is dead air you pay for only insofar as tokens are emitted, but it is dead air a user stares at.
• Steering latency — about 0.2 to 0.5 seconds of visual response at low network round-trip time. Google serves the model from the United States, Western Europe and Japan, and says higher latency outside those regions delays steering and can reduce frame rate. A product aimed at users in, say, Brazil or India is not running this at the frame rate the demos show.

出荷できるかどうかを決める制約
レート制限はリクエスト数ではなく同時セッション数で示される。これはストリーミングモデルには適切な単位だが、容量計画には扱いにくい単位だ。APIティア1では同時アクティブセッションが2つ、1日あたり50リクエスト。ティア2では5セッションと250リクエスト、ティア3では10セッションと1,000リクエストだ。セッション内の制御メッセージは別枠のクォータを消費しない。同時に2つのワールドを動かすのはデモ用の予算であって、ローンチ用の予算ではない。
能力のギャップも同じくらい重大です。なぜなら、それはアーキテクトが後になって初めて発見するものだからです:
• Genie 4では、関数呼び出し、構造化出力、コード実行、コンテキストキャッシュを利用できません。推論は別のモデルで実行し、テキストとして投入する必要があります。
• Batch API、Flex 推論、Priority 推論は利用できません。レイテンシとコストを引き換えにすることはできず、お金を払って列の先頭に割り込むこともできません。
• Safety filters are session-fatal, not request-fatal. Google's prompt guide says real human faces, public figures and recognizable brand IP can block a world_setup or close an active session mid-run — which, given the billing model, means a blocked session is a session you were paying for.
• Roughly a minute of usable coherence. Two minutes is the cap, 45 to 90 seconds is the honest working range, and Google lists camera latency, intricate physical interactions, audio precision and long-term scene permanence as open problems.
Genie 4 or Gemini Omni 1.2 Flash?
Both are video models with native audio on the same API key, and they answer different questions. Gemini Omni 1.2 Flash generates and edits fixed clips of up to 15 seconds, is generally available on the paid tier, charges $12.00 per million video tokens — about $0.07 per second at 720p, $0.023 at 360p, $0.104 at 1080p with upsampling, $0.209 at 4K — and can be batched, edited and upsampled offline. Genie 4 generates a world you steer in real time and cannot be scheduled, batched or cached at all.
• インタラクティブ vs. 固定 — Genie 4 はキー操作やセッション途中のプロンプトに反応します。Omni はクリップをレンダリングし、それを後から編集します。
• 1秒あたりのコスト — 720pではGenie 4が約0.10ドル、Omniが約0.07ドル(Omniのより安価な360pオプションとGenieの避けられないセッションオーバーヘッドを考慮する前)。
• 上限 — ライブストリームは120秒、クリップは15秒。ただし、クリップは4Kまで対応できるが、ストリームは最大720pまで。
• トランスポート — 永続的な WebRTC または WebSocket セッション vs. 通常のリクエスト。
• 運用負担 — Genie 4 にはセッションのライフサイクル管理と課金用キルスイッチが必要だが、Omni にはどちらも不要。
出力がショットなら、Omni を使え。出力がその中を誰かが歩き回るものなら、1 秒あたり 3 セントを余分に払い、運用上の負担を受け入れろ。
Pro Waitlistが実際に変えるもの
For a developer, nothing measurable. The Gemini API path to Genie 4 is gated by billing tier, not by subscription, and a Google AI Pro membership does not come with an API key that unlocks it. What the invitations in the signal change is the consumer side: Project Genie is drifting from a $99.99 Google AI Ultra feature toward something the $19.99 Google AI Pro tier can reach, which is roughly how Google has widened access to every Gemini-adjacent product it has shipped. If invitations are going out now, the reasonable planning assumption is broader Pro access in weeks, not quarters — but assume it, do not quote it, because Google has not published a date and the waitlist page still reads as a waitlist.
すでにAI Ultraを利用している場合でも、APIは別の課金体系で別のキーになります。サブスクリプションの割引が引き継がれることは一切ありません。
ストリーミングスタックにおけるルーターの位置づけ
Genie 4 is not on OrcaRouter and there is no honest way to pretend a stateful, per-second video stream is a chat completion. The reasoning half of a Genie pipeline is a different matter: the prompt construction, the event planning, the safety pre-checks and the post-session analysis are ordinary model calls, and Gemini 4 Argon at $2.00 / $10.00 per million tokens and Gemini 3.8 Flash at $0.75 / $3.75 per million are both live on our catalogue through one OpenAI-compatible key. That is one contract and one bill for the text side while the video side stays on Google's meter, and the 0% markup means a Google price change on those models lands on our side the same day rather than whenever a reseller reprices.
ここでは自動フェイルオーバーが通常のチャットワークロード以上に重要です。なぜなら、Genieセッションは安価に再試行できないからです。ワールドプロンプトを生成するプランニング呼び出しが失敗すると、セットアップのレイテンシを無駄にしたうえ、最悪の場合には有料セッションの一部まで失ってしまいます。その呼び出しをプロバイダー間にルーティングすることは、安上がりな保険なのです。

今週、誰がお金を使うべきか
テストしようとしているのが、インタラクティブな世界がユーザーの行動を変えるかどうかという点にあるなら、プロトタイプを作るべきだ — 空間デザインレビュー、エージェント訓練環境、監督がセットを歩き回りたいプレビジュアライゼーションのパスなど。2分間のセッションが12ドルなら、請負業者の1日分の時間のコストで50セッションを回せるし、720pという上限はその判断を左右する制約にはならない。
Wait if the thing you are testing is cost per output minute for finished video. Genie 4 is more expensive per second than Gemini Omni 1.2 Flash, capped at 720p, and offers no batch or priority path; the world model's advantage is that a human is inside it, and that advantage evaporates the moment your pipeline is unattended. Wait too if your users are outside the three serving regions, because the frame rate you demo in California is not the frame rate a user in São Paulo sees.
The open question worth watching is whether Google publishes an idle or paused-session rate. Right now the meter runs on streamed output until completion is called, which makes every Genie 4 integration a small exercise in billing discipline. A pause primitive, or a cheaper low-motion mode, would change the economics of this model more than any quality improvement in the next release.
