--- title: "TrueFoundry alternative — for coding tools · Selan" description: "TrueFoundry's AI Gateway routes Claude Code on an API key or each developer's own seat. Selan is hosted, one sign-in per person. Where each fits." url: https://selan.ai/compare/truefoundry updated: 2026-11-11T09:54:12+02:00 --- Compare · TrueFoundry and Selan # Is there a TrueFoundry alternative for a team's Claude Code? Yes, if the traffic is your team's coding tools and you want a gateway made for them, not an AI platform. TrueFoundry's AI Gateway is part of an AI platform that also governs MCP servers and agents and deploys models. It runs as SaaS, or in your own VPC, on-premises or air-gapped. Claude Code reaches it with a TrueFoundry key, and either an API key on the gateway or the developer's own Claude seat pays Anthropic. Selan is a hosted gateway that each developer signs in to once. If the gateway must run inside your own network, TrueFoundry is the better answer. ## How do TrueFoundry and Selan compare? | | TrueFoundry AI Gateway | Selan | | --- | --- | --- | | What it is | A gateway for models and MCP tools in an AI platform that also deploys, serves and fine-tunes models | A hosted gateway, with a CLI that launches Claude Code, Codex and OpenCode through it | | Where it runs | TrueFoundry's SaaS; your own VPC, on-premises or air-gapped on the Enterprise plan | A hosted service, built and hosted in the EU. Nothing to run | | Coding tools | Setup for Claude Code, Claude Desktop, Codex, OpenCode, Cursor, GitHub Copilot, Gemini CLI, Cline, Goose and more | Claude Code, Codex, OpenCode and Claude Desktop | | Claude for Claude Code | An Anthropic, Bedrock, Vertex or Microsoft Foundry account on the gateway, or each developer's own Claude seat passed through | The Claude and ChatGPT accounts and API keys your company connects | | A developer's credential | A TrueFoundry key or token per user, written by its setup tool or locked on each machine by MDM | One sign-in with Google or Microsoft through `selan login` | | Usage | Analytics per user with model, tokens and cost, and request logs with the prompt and response | One usage record per person, across every tool | | Limits | Budget rules per user, team, model or metadata, by day, week, month, quarter or lifetime, that block with a 429 or only warn | A spend limit per person, by day, week or month in UTC, on pay-per-use keys | | Content checks | Gateway guardrails on requests and responses, and Claude Code hooks that check prompts and tool calls | Secret scanning replaces a secret it recognises before the request leaves | | Cost | Developer free for up to 3 users; Pro $25 per user a month; Enterprise on a custom annual contract. Model costs are passed through | Free for up to three seats, no card | TrueFoundry governs every AI call a company makes, on a platform you configure. Selan is a gateway a team signs in to for its coding tools. ## When is TrueFoundry the better answer? When the gateway must sit inside your own network. On the Enterprise plan TrueFoundry runs in your VPC, on-premises or air-gapped, with data residency. When you want one platform for your own AI apps as well. The same gateway carries your apps' model calls, an MCP gateway governs their tools, and the platform deploys, serves and fine-tunes models. When Claude runs on your cloud account. A model account on the gateway can be Anthropic, Amazon Bedrock, Google Vertex AI or Microsoft Foundry. When you need more coding tools. TrueFoundry's table covers Cursor, GitHub Copilot, Gemini CLI, Cline, Goose, Qwen Code and Grok Build beside Claude Code, Codex and OpenCode. When IT must lock the setup on every laptop. Its setup tool writes Claude Code's `managed-settings.json`, which user and project settings cannot override, and MDM pushes it to the fleet. Claude Code hooks send prompts, shell commands, file edits and MCP tool calls to the gateway, which can block or rewrite them. If no team runs coding tools through a gateway, you do not need Selan. ## Who pays Anthropic when Claude Code goes through TrueFoundry? The credential that reaches Anthropic decides it. TrueFoundry documents two modes, and both give the gateway the same per-user attribution, budgets, rate limits, guardrails and logs. In API-key mode, the TrueFoundry key goes in `ANTHROPIC_AUTH_TOKEN`. The gateway calls Anthropic with the API key stored on its model account, so that key pays per token. The developer never signs in to Claude, and their seat, if they have one, is untouched. In subscription passthrough, the model account has no API key. The developer runs `/login` in Claude Code, and the gateway forwards their Claude login token to Anthropic untouched. The TrueFoundry key moves to an `x-tfy-api-key` header in `ANTHROPIC_CUSTOM_HEADERS`. Anthropic bills that developer's Enterprise, Team, Pro or Max plan. Passthrough works for Claude Code only, and only to Anthropic directly. Claude Desktop is always API-key mode through the gateway. A virtual model can try the developer's seat first and fall back to a pay-per-token key when the seat is rate-limited. **Good to know:** on passthrough, the cost TrueFoundry shows is an estimate at API list price; the seat is what actually pays. The Claude login token is short-lived, and a later 401 usually means `/login` again. ## How do TrueFoundry budgets work? A budget rule matches users, teams, models, provider accounts, virtual accounts or request metadata. Every matching rule is checked, and a request is blocked if any of them is over its limit. One rule can hold several limits at once. Days reset at 00:00 UTC, weeks on Monday, months on the 1st and quarters on the first day of each quarter; a lifetime limit never resets. An enforced rule answers with an HTTP 429. A warn-only rule lets requests through and still sends alerts at the thresholds you pick. An override on a per-user rule gives one person their own limit. Tenant admins manage tenant budgets, and team managers can manage their own team's. The Developer plan allows one budget rule, Pro up to ten and Enterprise any number. **Good to know:** a budget counts spend from when the rule was created, not from the start of its period. A per-user rule does not cover requests made with a virtual account token; those need a per-virtual-account rule. ## When is Selan the better answer? When the traffic is a team's coding tools and nobody wants to configure each tool. A developer runs `selan login`, then `selan claude`, `selan codex` or `selan opencode`. Claude Desktop goes through the same gateway with one settings file. Claude Code, Codex, OpenCode and Claude Desktop go into one usage record per person. A limit per person applies across every pay-per-use key. An owner connects the company's accounts and keys once, and switches on the models the team may use. No provider key reaches a laptop. With secret scanning on, a secret it recognises is replaced before the request leaves. The trade-off is that requests travel through Selan, so if Selan is unavailable those requests fail. Your accounts can still be used directly. Which providers serve which models is in [models and providers](https://selan.ai/docs/providers), limits per person are on [the spend page](https://selan.ai/solutions/spend), and scanning is in [the secret scanning docs](https://selan.ai/docs/secrets). ## How do you move Claude Code from TrueFoundry to Selan? Run `tfy-local-ai-setup uninstall` if TrueFoundry's setup tool configured the machine. Otherwise remove `ANTHROPIC_BASE_URL`, `ANTHROPIC_AUTH_TOKEN` or `ANTHROPIC_CUSTOM_HEADERS` and the `ANTHROPIC_DEFAULT_*_MODEL` lines from the `env` block of `~/.claude/settings.json`. A `managed-settings.json` pushed by MDM is removed by whoever manages your machines. Then run `selan login` and `selan claude`. Connect the company's Anthropic accounts or keys in Selan and switch on their models. You can keep TrueFoundry for your own apps and run the team's coding tools through Selan. Keeping provider keys off laptops is covered in [Claude Code without API keys on laptops](https://selan.ai/guides/claude-code-without-api-keys), and the kinds of gateway in [Claude Code gateways](https://selan.ai/guides/claude-code-gateway). [Start for free](https://auth.selan.ai/r) Free for up to three seats, and the Free plan needs no card. ### The short version - TrueFoundry's AI Gateway is part of an AI platform, run as SaaS or in your own VPC, on-premises or air-gapped. - Claude Code reaches it with a TrueFoundry key; an API key on the gateway or each developer's own Claude seat pays Anthropic. - Budget rules match users, teams, models or metadata, reset in UTC, and block with a 429 or only warn. - Selan is hosted in the EU: one sign-in per person, no provider key on the laptop, and a spend limit per person. What TrueFoundry does is as TrueFoundry's documentation (Claude on TrueFoundry, Claude Code, Enforce Claude settings with MDM, Set up your IDE, coding agents and AI apps, Budget Limiting, and the Budget Limiting V2 and plan-based feature gating announcements) and its pricing page described it, read on 11 November 2026. It changes: check the date before relying on it. What Selan does is as its CLI and docs stated it on that date.