Tokens On Me

Use an allowance in oh-my-pi

oh-my-pi talks to Tokens On Me as it would to OpenAI or Mistral, with your token in place of their key. The commands create a separate profile for your allowance.

Before you start

  1. Install oh-my-pi using the official instructions.
  2. Open your invitation or claim link, confirm you are 18 or older, and copy your token. It is shown only once. If you lose it, open the allowance in Allowances and replace the token.

For an allowance on Mistral, oh-my-pi is the tool to use: Mistral’s terms do not let its own coding tool, Vibe, be used through a service like this one.

Start using your allowance

The token’s page gives these lines with your token and your allowance’s models filled in. They write oh-my-pi’s settings for the allowance, then start it. For an allowance on GPT:

mkdir -p "$HOME/.omp/profiles/tokens-on-me-openai/agent"
cat > "$HOME/.omp/profiles/tokens-on-me-openai/agent/models.yml" <<'EOF'
providers:
  openai:
    baseUrl: https://tokens-on.me/openai/v1
    apiKey: TOKENS_ON_ME_OPENAI_TOKEN
EOF
export TOKENS_ON_ME_OPENAI_TOKEN=tom_…
omp --profile tokens-on-me-openai --model openai/gpt-6.1-sol \
  --slow openai/gpt-6.1-sol --plan openai/gpt-6.1-sol --smol openai/gpt-6-luna

For an allowance on Mistral:

mkdir -p "$HOME/.omp/profiles/tokens-on-me-mistral/agent"
cat > "$HOME/.omp/profiles/tokens-on-me-mistral/agent/models.yml" <<'EOF'
providers:
  mistral:
    baseUrl: https://tokens-on.me/openai/v1
    apiKey: TOKENS_ON_ME_MISTRAL_TOKEN
EOF
export TOKENS_ON_ME_MISTRAL_TOKEN=tom_…
omp --profile tokens-on-me-mistral --model mistral/mistral-medium-3-5 \
  --slow mistral/mistral-medium-3-5 --plan mistral/mistral-medium-3-5 --smol mistral/mistral-small-2603
--profile
A separate profile for each provider, with its own settings, sessions and history.
models.yml
Sends oh-my-pi’s requests for that provider to Tokens On Me, with the token from the variable the lines export.
--model, --slow and --plan
Uses the allowance’s first model for conversations, extended thinking and planning.
--smol
Uses the allowance’s last model for quick background tasks. Requests to models outside the allowance are rejected.

Anyone with your token can spend your allowance. Keep it out of shared files and version control. If it leaks, replace it from the allowance’s page to stop the old token immediately.

For later sessions, run the last three lines in a new terminal. The settings are already saved.

All guides