The AI router for greener, sovereign AI.
One API to the major LLM providers, hosted in Europe, with sovereignty on your terms and a carbon receipt on every call. We're a proxy: your prompts pass through to the provider you chose. Never retained, never transformed, never trained on by us. We keep only per-request metadata for billing, and your chosen provider handles the prompt under its own terms.
Paste it into the custom-provider screen of Cursor, Claude Code, OpenCode, Aider, Cline, or Goose. You don't need a plugin or a proprietary protocol.
One metered hop between your app and the provider
Your app or agent
LowRouter
Provider you chose
auto mode: eligible models → lowest carbon → lowest cost → round-robin
Every response returns with lowrouter_metadata: provider, region, gCO₂eq emitted, and grid carbon intensity. Cost per call comes back inline in usage.cost (streaming included) and lands in your dashboard.
One invoice for all your AI providers
Stop juggling provider accounts, prepaid balances, and stranded credits. You pay LowRouter; we pay the providers.
- One balance, pay-as-you-go. Top up when you need to, with no seats and no commitment.
- Token usage billed at the upstream provider's per-token price, converted to EUR, with no per-token markup. Fees apply at top-up only, published on the pricing page and shown before you confirm.
- One EU VAT-compliant invoice for finance, whatever mix of providers you used.
What LowRouter records for every request
Your dashboard breaks down usage across every provider you route to: tokens in and out, upstream cost, and gCO₂eq emitted. Export it as CSV: auditable, per-request data your ESG team can put toward Scope 3 reporting.
Finance and sustainability reports come from the same source of truth.
| Model | Provider | Tokens | Cost | gCO₂eq |
|---|---|---|---|---|
| mistral-large | mistral | 1,204,880 | €3.10 | 41.2 |
| mistral-small | scaleway | 2,051,300 | €1.28 | 22.7 |
| claude-haiku-4.5 | anthropic | 838,540 | €1.90 | 78.5 |
| gpt-4o-mini | openai | 521,010 | €0.74 | 66.0 |
| llama-3.3-70b | groq | 149,200 | €0.11 | 9.4 |
| Total | 4,764,930 | €7.13 | 217.8 |
Keep your existing OpenAI client
There is no LowRouter SDK and no proprietary protocol. Point anything OpenAI-compatible at https://api.lowrouter.ai/v1.
- SDKs
- OpenAI PythonOpenAI NodeLangChainLiteLLMany OpenAI-compatible…
- Coding agents
- Claude CodeOpenCodeGooseAiderClineCursor…
It's just a base URL, so you can switch back any time.
Aliases
Call alias/my-model in your code; repoint it to any provider, model, or region later without changing client code.
Auto-routing
Set a policy once, such as a carbon budget per key, and LowRouter picks the route that fits for each request.
A sovereign platform, with carbon estimates you can audit
Sovereign
The platform: LowRouter runs in France, operated by Carbonifer SAS (Nantes). It is GDPR-native and outside CLOUD Act reach. Your keys, billing data, and usage metadata never touch US jurisdiction.
The inference: your choice. Filter the catalogue to EU-only providers and pin an alias to a specific provider, model, and region. The region we routed to is reported in every response.
Carbon transparency
Per-request gCO₂eq in every response, computed from open public grid data (Ember Climate, refined by regional grid operators: RTE, PJM, CAISO, National Grid ESO, AEMO…) and the EcoLogits energy model.
Pick the lowest-carbon route. Compare providers by carbon intensity per token in the catalogue and choose the cleanest one that fits, or name the model with auto/<creator>/<model> and let us pick the route for it.
These are estimates. They come from regional grid averages applied to modeled inference energy. They are not lifecycle emissions, and not meter readings from the provider's datacenter. When we can't classify a request, we report unknown rather than fabricate a number. Read the methodology and what it deliberately leaves out.
From your first request to an auditable receipt
- 01
Point your SDK at us
Change the base URL to api.lowrouter.ai/v1. That is the only change.
- 02
Pick your route
A full model ID (mistral/mistralai/mistral-large-2512/eu) to pin the route, auto/<creator>/<model> to name the model and let us pick the greenest route for it, or one of your aliases. Compare carbon, cost, and jurisdiction in the catalogue first.
- 03
Read the receipt
Every response carries lowrouter_metadata with the provider, region, gCO₂eq, grid intensity, and cost. You can log it for audits or show it to your users.
Usage-based pricing, without seats or commitments
Token usage is billed at the upstream provider's per-token price, converted to EUR, with no per-token markup. Our fees apply once, when you top up credits: a payment-processing fee and a small LowRouter fee, with the exact numbers published on the pricing page. There is no monthly commitment and no per-seat charge.
Top up credits when you need them, and the exact fees are shown before you confirm. Your dashboard then breaks down tokens, cost, and gCO₂eq per model and provider you've used, so finance and sustainability reporting come from the same source of truth.
What we claim, and where it's proven
| Claim | Where it's proven | Docs |
|---|---|---|
| Carbon transparency | Every response carries lowrouter_metadata with the region, grid carbon intensity, and gCO₂eq of that call. The formula behind it is published. | Methodology → |
| EU sovereign | The platform runs in France, operated by Carbonifer SAS (Nantes). Your keys, billing data, and usage metadata stay in EU jurisdiction; the routed region is returned on every response. | Sovereignty → |
| One API, one bill | Many providers sit behind one OpenAI-compatible API, with one balance and one EU VAT invoice. Tokens are billed at the upstream per-token price in EUR; fees apply at top-up only and are published in full. | Billing → |
| No lock-in | It's just a base URL. Call an alias and repoint it to any provider, model, or region later, or point your SDK back at a provider directly at any time. | Integration → |
Why we built this
We kept having to answer "what does our AI actually emit?" with vendor marketing instead of data. Carbonifer's job is measuring software's footprint, and the router is the one hop every request already crosses, so that's where we put the meter. If a number on this page can't be traced to a source, we'd rather not show it.
— Olivier, founder
Design decisions
- Missing carbon data is reported as unknown, never as an average. We would rather show a gap than an estimate you can't trace.
- Sovereignty constraints beat carbon optimization. If you pin EU-only, we route EU-only, even when a lower-carbon region exists elsewhere.
- Repointing an alias trades reproducibility for flexibility. That's your call, so repointing is a named, visible action that we never take silently.
Frequently asked questions
More questions? See the full FAQ in the docs.
What is LowRouter?
An AI router (a gateway/proxy): one OpenAI-compatible API in front of many LLM providers. We forward your request to the provider you chose and return the response with a carbon and cost receipt. We don't run models ourselves.
Are you an LLM provider?
No, we're a proxy. Your prompt goes to the provider you picked, with streaming intact. We don't read, store, transform, or train on it.
Why do you list US and non-green providers at all?
Because you can't choose responsibly without seeing the alternatives. LowRouter shows the region, jurisdiction, and carbon cost of every route, including the non-sovereign and carbon-heavy ones, so you can compare them and decide. Sometimes you need a specific US model; you can use it and see exactly what it emits. Putting every provider on the same public scoreboard also gives them a reason to compete on it: when a provider ships greener or more sovereign inference, it shows up here with measured figures.
Can I pin requests to a specific country or jurisdiction?
Yes. Pin an alias to a provider, model, and region, or filter the catalogue to EU-only. The routed region is returned in every response.
How accurate are the carbon numbers?
They're estimates built only on open, citable sources: Ember Climate country averages refined with regional grid-operator data, and EcoLogits for inference energy. Every assumption is documented in the methodology.
Do you use my data?
No. We don't train on your prompts, run analytics on their content, or resell them. Requests are forwarded without being stored; only billing metadata (tokens, model, cost, carbon) is kept for your dashboard.
How does pricing work?
Upstream per-token prices are converted to EUR with no per-token markup. Fees apply once, at credit top-up. The exact amounts are published on the pricing page and itemized before you pay.