⚡ Your AI bill is eating your Q4 margin.Protect Your Margin. Get a FREE 360° Cost ReportFree 360° Cost Report

Home › Docs › Coding tools

Get started

Coding tools

Point AI coding tools at apicuts using native Anthropic Messages, OpenAI Responses, or OpenAI-compatible Chat Completions so your coding spend gets the same savings as production.

Sign up, fund your prepaid wallet in /app/funding, and generate an ack_... key in /app/keys (store it in $APICUTS_API_KEY). Use https://apicuts.ai for Anthropic tools such as Claude Code, and https://apicuts.ai/v1 for OpenAI-compatible, Responses, and Gemini-via-OpenAI tools (native Gemini format is on our roadmap). You can also install the macOS Companion V1 with one command, or book a free 360° Cost Report.

Shell
# Install macOS Companion V1 (configures supported local tools)
curl -fsSL https://apicuts.ai/install | sh -s -- --key "$APICUTS_API_KEY"

# List live enabled model IDs for your key
curl -sS "https://apicuts.ai/v1/models" \
  -H "Authorization: Bearer $APICUTS_API_KEY"

Claude Code

Claude Code speaks Anthropic's native Messages API, which apicuts serves live at /v1/messages. Set ANTHROPIC_BASE_URL to https://apicuts.ai without /v1 (the client appends /v1/messages):

Shell
export ANTHROPIC_BASE_URL="https://apicuts.ai"
export ANTHROPIC_AUTH_TOKEN="$APICUTS_API_KEY"
export ANTHROPIC_MODEL="claude-sonnet-5-5"
claude

Codex CLI

Point Codex CLI at the live /v1/responses endpoint in ~/.codex/config.toml:

~/.codex/config.toml
model_provider = "apicuts"
model = "gpt-6.1-sol"

[model_providers.apicuts]
name = "apicuts"
base_url = "https://apicuts.ai/v1"
env_key = "APICUTS_API_KEY"
wire_api = "responses"

Cursor

Open Cursor's settings and go to Models. Paste your ack_... key from /app/keys into the OpenAI API key field, enable overriding the OpenAI base URL, set it to https://apicuts.ai/v1, and add live model IDs returned by GET /v1/models (such as gpt-6.1-sol). Note: custom gateways on /v1/chat/completions require streaming enabled and a unique Idempotency-Key header per request; tools that do not send Idempotency-Key should use Responses or native Anthropic endpoints where supported. Some Cursor features run on Cursor's own models and bypass custom keys.

Continue

Add apicuts in your Continue config.yaml. Prefer Anthropic Messages (https://apicuts.ai) or OpenAI-compatible https://apicuts.ai/v1 with streaming enabled:

config.yaml
models:
  - name: apicuts-gpt
    provider: openai
    model: gpt-6.1-sol
    apiBase: https://apicuts.ai/v1
    apiKey: $APICUTS_API_KEY
  - name: apicuts-claude
    provider: anthropic
    model: claude-sonnet-5-5
    apiBase: https://apicuts.ai
    apiKey: $APICUTS_API_KEY

When using /v1/chat/completions, apicuts requires stream: true and a fresh Idempotency-Key header on each call; /v1/messages and /v1/responses do not require Idempotency-Key.

Cline

In Cline's settings, choose Anthropic (Base URL https://apicuts.ai, model claude-sonnet-5-5) or OpenAI Compatible (Base URL https://apicuts.ai/v1, model gpt-6.1-sol or a live Gemini ID from GET /v1/models), then enter your $APICUTS_API_KEY (ack_...).

Aider

With Anthropic Messages (recommended for Aider since no extra Idempotency-Key header is needed):

Shell
export ANTHROPIC_BASE_URL="https://apicuts.ai"
export ANTHROPIC_API_KEY="$APICUTS_API_KEY"
aider --model anthropic/claude-sonnet-5-5

Or via OpenAI-compatible Responses / Chat Completions (ensure streaming and a per-request Idempotency-Key header if targeting /v1/chat/completions):

Shell
export OPENAI_API_BASE="https://apicuts.ai/v1"
export OPENAI_API_KEY="$APICUTS_API_KEY"
aider --model openai/gpt-6.1-sol

Any other tool

Any CLI, agent, or editor that accepts an Anthropic base URL (https://apicuts.ai) or an OpenAI base URL (https://apicuts.ai/v1) works with apicuts. See SDKs and integrations for exact request headers and code examples.

Running Claude Code across an engineering team? Model turn-by-turn cache and monthly seat spend in the Claude Code Cost Calculator, review Claude Code team cost controls, or read why Claude Code burns API tokens fast.

Want us to find your 20%+?

Get a free 360° cost report. Bring last month's provider usage and we'll show you your biggest waste and the first fix we'd ship.

Get a Free 360° Cost Report