Sakana FuguをClaude Codeで利用する設定方法と、利用時に残る3件の制約

This orchestration upgrade resulted in gains of up to 7.9 points over v1.0, with particularly strong results on ProgramBench and Terminal Bench 2.1. Fugu-Ultra v1.1 is demonstrably more capable across coding, agentic tasks, and advanced reasoning. ／ Crucially, this massive leap in reasoning capabilities is available today at the same price as Fugu-Ultra v1.0. — 性能向上と価格に関する記述より

By dynamically orchestrating the latest frontier models, we pushed performance up by as much as 7.9 points. We are now beating leading models like Fable 5 in complex coding and reasoning tasks, without even having Fable in our agent pool. — Fable 5 との比較に関する記述より

Our Fugu models surpass publicly accessible frontier models and are shoulder-to-shoulder with Fable 5 and Mythos Preview in various rigorous engineering, scientific, and reasoning benchmarks while delivering frontier capability without the risk of export controls. ／ For Fable 5 and Mythos Preview, we report the max of the two if both scores are available on the same benchmark. Neither of them is in Fugu’s agent pool as they are not publicly accessible. — 製品ページ側の「肩を並べる」という主張、および Fable 5 がエージェントプールに含まれていない理由に関する記述より

Today, we’re making Fugu more accessible again with Claude Code-compatible endpoints for Sakana Fugu. ／ You can now bring Fugu’s multi-agent intelligence directly into Claude Code. This puts a dynamically coordinated team of frontier models to work inside the coding workflow you already know and love. Instead of relying on a single model to write, debug, and execute your code, you can now orchestrate a diverse pool of state-of-the-art models directly from your terminal. — Claude Code 互換エンドポイントの発表に関する記述より

Before using Fugu or Sakana Namazu, create an API key and copy the generated key. The key is shown only once, so store it somewhere secure before closing the dialog. — APIキーの作成に関する記述より

Sakana Fugu plugs into the Codex CLI and Claude Code through a small provider configuration. To quickly get started, you can install Fugu with a single command: ／ curl -fsSL https://sakana.ai/fugu/install | bash ／ Then launch Codex with: ／ codex-fugu ／ or Claude Code with: ／ claude-fugu ／ The one-line install supports Ubuntu and macOS. On Windows, or if the install does not complete in your local environment, set it up by hand: see Manually Setting Up Codex for Codex, or Manually Setting Up Claude Code for Claude Code. — インストール手順と対応OSに関する記述より

git clone "$REPO_URL" "$REPO_DIR" ／ bootstrap: no terminal for the menu and FUGU_INSTALL_TARGET is unset; defaulting to Codex. ／ bootstrap: local changes in %s will be discarded by the update. — インストーラのスクリプト本文より

Claude Code points at Sakana Fugu through a set of ANTHROPIC_* environment variables, with no launcher required. The quickest way is to export them in your current shell session and then run claude. Use ANTHROPIC_AUTH_TOKEN (a bearer token), not ANTHROPIC_API_KEY. ／ This lasts for the current shell session. ／ Save the following to ~/.codex/fugu.json. The base_instructions carry Sakana Fugu's shipped agent-conduct safety guards — 手動設定の手順と、Codex 側モデルカタログの保存先に関する記述より

Note: model="fugu-ultra-v1.1" supports three reasoning effort levels: high, xhigh, and max (a distinct maximum level for the hardest problems). model="fugu-max", model="fugu-ultra" (Fugu Ultra v2.0), model="fugu", model="fugu-ultra-v1.0", and model="fugu-cyber" support high and xhigh (max is also accepted for compatibility and maps to xhigh). ／ The Opus tier maps to fugu-max[1m], Sonnet and Haiku to fugu[1m], and the Fable tier to fugu-ultra[1m]; subagents use fugu[1m]. Sessions start on fugu-max[1m] at high effort. ／ Two models are optional extras rather than tiers. Add ANTHROPIC_CUSTOM_MODEL_OPTION="fugu-ultra-v1.1[1m]" to get a pinned Ultra release row in /model, and point a tier at fugu-cyber[1m] only if your key is approved for it. — エフォート段階、モデル対応、任意で追加できるモデルに関する記述より

Claude Code is closed source, so Sakana Fugu drives it entirely through the documented ANTHROPIC_* variables and our server-side gateway. A few surfaces therefore reflect Claude Code's built-in Anthropic assumptions rather than Fugu's lineup, and they are cosmetic only: the model you talk to, its responses, streaming, tool use, and subagents all behave exactly as configured. ／ Effort slider. Claude Code shows six stops (low through ultracode); Fugu maps them onto its two real levels at the high / xhigh boundary, so stops within a group are equivalent. ／ Model picker. On recent Claude Code, claude-fugu replaces the built-in tier list with one row per Fugu model, so the picker matches the lineup above. On older clients, or in a manual setup, Sonnet and Haiku both resolve to fugu[1m], so two identical rows appear; without curated labels, descriptions name the Anthropic tier rather than the Fugu model. ／ Session header. Billing and default-tier labels reflect API-token usage. ／ Because Claude Code evolves independently, new cosmetic mismatches may surface over time. — Claude Code との互換性に関する記述より

Note that the claude-fugu launcher does not auto-update: to pick up the latest Fugu support for Claude Code, such as new Fugu models, check this Get Started page and apply the update manually. — ランチャーの自動更新に関する記述より

The claude-fugu launcher does not auto-update, so to pick up the latest Fugu support for Claude Code (such as new Fugu models), re-run the install, or redeploy the configs as in Manually Setting Up Claude Code — ランチャーの更新方法に関する記述より

The fugu model routes across all supported providers by default. If you need to opt out of a provider for fugu routing, enable Fugu custom model pool while creating or editing the API key, then leave only the providers you want fugu to use. Leave the setting off to use the full default pool. — ルーティング先の制御に関する記述より