The key carries the DEK.
Claude Code
OpenAI
AnthropicDeepSeekCohere
OpenAIQwenPerplexity
GeminiMistralZhipu
GrokMinimax

Every model you already pay for. Behind one key.

Route any endpoint through the ChatGPT, Claude, Grok, and Kimi subscriptions you already pay for — no markup. Works in your app, IDE, and CLI.

The server stores ciphertext. Nothing else.
Anthropic
OpenAI
Google
Bedrock

Every model you already pay for. Behind one key.

Route any endpoint through the ChatGPT, Claude, Grok, and Kimi subscriptions you already pay for — no markup. Works in your app, IDE, and CLI.

AnthropicDeepSeekCohere
OpenAIQwenPerplexity
GeminiMistralZhipu
GrokMinimax

Every subscription, one endpoint

Claude Pro / Max, ChatGPT Plus, Kimi Code, SuperGrok — plans you already pay for. A small daemon on your machine serves them through the official vendor CLIs, so subscription traffic never touches our cloud.

Plans it serves

Claude
OpenAI
Kimi
Grok
+ more

More as vendors ship official CLIs.

One command to install

Install with one command; connect from the dashboard.

Same sk-llm key

Subscriptions become more models in your chains — no new credentials.

Only on your hardware

The cloud refuses subscription traffic — it runs on machines you own.

Know what your plans are worth to you

OpenLLM privately estimates what your usage would cost at metered list prices — so you can see what your plans are worth, and right-size what you pay for.

An estimate, not a bill

Computed from public list prices. Informational only — it never touches what you owe.

Your account, your data

Built from usage your own accounts report via official tooling. Private to your dashboard — never shared.

Honest both ways

If a plan isn't paying for itself, the card shows that too.

Estimates are informational and may differ from actual pricing. Plan names belong to their vendors; subscriptions stay governed by each vendor's terms, served on your device through official tooling.

Know what every token costs

Model, tokens, latency, dollars — and which hop actually answered. Metadata only; prompts are never stored.

Providers
OpenAIOpenAIActive
GoogleGoogle AIActive
KimiKimiActive
BedrockAWS BedrockOff
Claude
ClaudeMax
Active
5h window42% · 1h 20m until reset
Monthly ≈ $184 saved · $92 left

Every provider, one panel

Paste a key — encrypted before it leaves your browser — or sign in on your daemon. Each card shows what it unlocks and whether it's live.

model: "ultra"opus-5gpt-5.3model: "plus"sonnet-5qwen3.7model: "lite"haiku-4-5glm-4.7

Fallback chains

Ask for a chain, not a model. Whatever fails, the next hop answers.

localhost:11434/v1probed /v1/models · 6 foundllama-3-70b+5

Custom endpoints

Any host you can reach — even one on your laptop. Its models route like ours.

MacBook-Ask-llm-a91.****This device · v1.8.6Berlin, DE · last seen 2m agosk-llm-7f2.****idleUbuntu box · Cursorsk-llm-0c8.****revokedCI runner · revoked 3d ago

Scoped keys

One key per app or device. Its own spend, its own cooldown, revoked alone.

provider bill$18.40markup$0.00plan billed flat, not per token

No markup

Your keys, your provider's bill. We charge a flat plan, never a cut.

Free to start

50M tokens a month, free

No card, no trial clock. Bring your own provider keys, run 2 devices, and keep every request encrypted end-to-end. Upgrade only when you outgrow it.

Need more? Pro lifts the monthly cap — 7-day free trial.

Zero-knowledge, not "trust us"

Keys are AES-256-GCM encrypted in your browser, under a recovery phrase only you hold. We store ciphertext; the decryption key arrives only inside your sk-llm key, lives in memory for the request, then is zeroed.

  • No master key exists — we couldn't decrypt your vault if subpoenaed.
  • A breach of our database leaks nothing usable.
  • Lose the phrase? Reset and re-paste — we can't recover it, by design.

The questions you're actually asking

Can't find what you're looking for? Contact our customer support team

Can't find what you're looking for? Contact our customer support team