Does the Kottos AI trial work with a Claude subscription?

Yes. Claude Code sends its own login or API key in the Authorization header. The gateway passes it through to Anthropic unchanged and never stores it. The trial key only labels the traffic as the trial.

Does the gateway slow Claude Code down?

The gateway itself adds microseconds; the network hop to it adds the round trip from your machine to our host, which depends on where you are. Time to first token is dominated by Anthropic's own queue and generation.

What does Kottos AI record?

Timing stamps, the model, the venue, token counts including cache reads and writes, status and errors. There is no field for prompt text and no field for the credential; the record layout is public in the llmbridge repository.

Public Claude Code demo

1 / Setup

Two lines.

For this trial, you only need to update ANTHROPIC_BASE_URL and ANTHROPIC_CUSTOM_HEADERS in Claude Code settings. The first variable needs to point your requests to the Kottos AI gateway, and the second needs to contain the token that gives you permission to use the trial account. Note that we have throttles in place as a safety measure.

Open ~/.claude/settings.json (or the project's .claude/settings.local.json) and add the env block below to it:

// ~/.claude/settings.json
{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.kottos.ai",
    "ANTHROPIC_CUSTOM_HEADERS": "x-kottos-key: kb_live_sPWBYzmGGOIqkCPUPbAfxsSwj6K-8iWJ"
  }
}

The settings filename is always the same but location may depend on the platform: for Linux or macOS ~/.claude/settings.json, and for Windows %USERPROFILE%\.claude\settings.json on Windows.

If you prefer a terminal, set the two as environment variables: export ANTHROPIC_BASE_URL=https://api.kottos.ai and export ANTHROPIC_CUSTOM_HEADERS="x-kottos-key: kb_live_sPWBYzmGGOIqkCPUPbAfxsSwj6K-8iWJ" for Linux or macOS, and $env:ANTHROPIC_BASE_URL="https://api.kottos.ai" and $env:ANTHROPIC_CUSTOM_HEADERS="x-kottos-key: kb_live_sPWBYzmGGOIqkCPUPbAfxsSwj6K-8iWJ" for Windows.

Claude Code picks the config changes automatically so there is no need to restart. After you add the env block, check the dashboard data.kottos.ai/trial and your requests should appear as they complete. If you want to stop the trial, simply remove the env block.

2 / What you see

The requests metadata.

This public demo shows request measurements on a single provider. It is a way to inspect the request path, not the full self-serve product or enterprise service. To use the live self-serve product, create an account and start with $10 in Kottos credits. Teams that need a dedicated service can discuss an enterprise design partnership.

// per model

Net $ per million tokens

The net effective rate is an important number to consider when deciding on a model or provider. This is what you are billed on.

// per request

Time to first token

The gateway measures the timing at different steps of the request path so we understand your timing bottlenecks. You can analyze one of them which is the time to first token.

// reliability

Errors, retries, truncation

If a request does not come back or is partially completed, you can also see its status. If you hit rate limits or 5xx errors, those are examples of prompts not completed by the provider.

The public demo dashboard is shared and public so everyone on the trial will share resources. We do not show identifying data.

3 / Security is a priority

Privacy behind everything we do.

The record for each request is a fixed byte layout that does not allow for prompt or responses text, nor credentials. Credential headers are also scrubbed after each request is processed. Additionally, all connections run with TLS.

What the demo is

A measurement. We forward your request to Anthropic byte for byte and record what comes back. There is no change, i.e. the model does not change, the venue is always anthropic direct, and tokens are the same.

What the demo is not

A self-serve account. The demo is shared and public, and uses your Anthropic plan. To use the live Kottos AI product, create an account and start with $10 in Kottos AI credits.

4 / Questions

Demo FAQ.

Does it work with a Claude subscription?

Yes. Claude Code sends its own login in the Authorization header, the gateway passes it through, and Anthropic answers normally. We run our own sessions this way.

Does it slow Claude Code down?

The gateway adds microseconds to the request path. The only noticeable latency could be the trip latency added by going through the gateway server. This is capped at 120 ms within the US. This number is still small compared to TTFT and also depends on where you send the request from. If this is something that matters for your work, reach out to us because this is exactly the type of problems Kottos AI optimizies for.

Why is the trial key public?

We believe that a trial should take seconds to setup and not require a sign-up.

How do I leave?

Delete the two lines. Once these are removed, Claude Code goes back to talking to Anthropic directly. There is no need to restart Claude Code either.

Open the public demo dashboard ↗ Get $10 in credits

What does your
Claude Code
actually cost?