Claude Code with 6bee.ai

Before you start

• Claude Code installed (npm install -g @anthropic-ai/claude-code).
• Create an account with a verified email address, add prepaid balance, then create a key on the console's API keys page. Keep the key secret.
• Model IDs are listed in the console and returned by GET https://api.6bee.ai/v1/models. Replace <model id> with one of them.

Set the environment variables

Run these in the shell you start Claude Code from:

export ANTHROPIC_BASE_URL=https://api.6bee.ai
export ANTHROPIC_AUTH_TOKEN=<your key>
export ANTHROPIC_MODEL=<model id>
export ANTHROPIC_DEFAULT_HAIKU_MODEL=<model id>   # background tasks
claude

ANTHROPIC_BASE_URL

The 6bee.ai host, without /v1. Claude Code adds /v1/messages itself.

ANTHROPIC_AUTH_TOKEN

Your 6bee.ai key, sent as a Bearer token.

ANTHROPIC_MODEL

The model for the main conversation.

ANTHROPIC_DEFAULT_HAIKU_MODEL

The model for background tasks such as titles and summaries. Set it, or those calls ask for a model 6bee.ai does not list.

Make it permanent

To avoid exporting the variables in every shell, put them in Claude Code’s settings file:

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.6bee.ai",
    "ANTHROPIC_AUTH_TOKEN": "<your key>",
    "ANTHROPIC_MODEL": "<model id>",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "<model id>"
  }
}

This file holds your key in plain text. Do not commit it to a repository.

Check that it works

1. Start claude in a project folder.
2. Send a short message. The reply comes from the model you set.
3. Open the console’s usage log: the request appears there with its token counts and cost.

Limits that matter for long sessions

Context

Input plus output up to the model’s window: 128K to 1M tokens, depending on the model.

Output

max_tokens up to the model’s output cap: 16,384 to 131,072, depending on the model. Larger values are lowered to the cap, not rejected. If omitted: 8,192 to 32,768.

Input tokens

1,000,000 uncached tokens per rolling minute. Cache hits don’t count.

Requests

60 per minute.

Concurrency

2 requests at a time.

Request body

Up to 8 MiB. n must be 1.

Over a limit you get HTTP 429 with Retry-After, or 400 when a request can’t fit the context. A lowered output cap is reported in the X-6bee-Output-Cap response header; on /v1/messages a thinking budget is lowered with it.

Troubleshooting

HTTP 401

The key is missing or wrong. Copy it again from the console, without spaces or quotes.

Model not found

The model ID does not match. List the valid IDs with GET /v1/models or check the console.

HTTP 429

You are over a per-account limit (requests, input tokens or concurrency). The Retry-After header says how long to wait.

HTTP 400 on long sessions

The request no longer fits the model’s context window. Compact or clear the conversation, or switch to a model with a larger window.

Request rejected for balance

Each request first reserves its input plus max_tokens of output. Top up, or lower max_tokens.

A model you did not set is requested

Set ANTHROPIC_DEFAULT_HAIKU_MODEL as well. Claude Code uses it for background tasks.