Try every CLI tool, no card
/ one-time
1M · no expiry
1M tokens, valid across Claude Code, Gemini CLI, and OpenAI CLI. Never expires.
ClaudeOpus 4.8
Sonnet 4.6
Haiku 4.5
Gemini2.5 Pro
Flash
Flash-Lite
OpenAIGPT-5.5
5 mini
5 nano
A flat monthly fee, a 5-hour token window, and the latest frontier models in your terminal. One API key, one shared wallet — no idle GPU cost, no surprise overage, no API rate gymnastics.
Annual
2 months free
1M · no expiry
1M tokens, valid across Claude Code, Gemini CLI, and OpenAI CLI. Never expires.
2 months free · save $50
3M · 5-hour window
3M tokens every 5-hour window, with all the latest models across every supported CLI.
2 months free · save $70
5M · 5-hour window
5M tokens every 5-hour window, with priority queue and full usage analytics.
2 months free · save $160
20M · 5-hour window
20M tokens every 5-hour window, for teams running CLIs around the clock.
Pick the plan that matches your CLI workload. Upgrade or downgrade any time.
| Feature | Test | Pro | Max | Ultra |
|---|---|---|---|---|
|
Tokens per 5-hour windowTest is one-time, others reset on a rolling 5h window
|
1M (one-time) | 3M | 5M | 20M |
|
Monthly billing
|
$3 one-time | $25 / mo | $35 / mo | $80 / mo |
|
Annual billingPay for 10 months, get 12 — 2 months free
|
— | $250 / yr Save $50 |
$350 / yr Save $70 |
$800 / yr Save $160 |
|
CLI tools supportedClaude Code, Gemini CLI, OpenAI CLI
|
All 3 | All 3 | All 3 | All 3 |
|
API keys includedOne key works across all 3 CLIs — no per-tool key needed
|
1 | 1 | 1 | 1 |
|
Top 3 frontier models per providerClaude: Opus 4.8 · Sonnet 4.6 · Haiku 4.5 | Gemini: 2.5 Pro · Flash · Flash-Lite | OpenAI: GPT-5.5 · 5 mini · 5 nano
|
✓ | ✓ | ✓ | ✓ |
|
Priority queue
|
— | — | ✓ | ✓ |
|
Concurrent CLI sessions
|
1 | 3 | 5 | 10 |
|
Usage analytics & alerts
|
— | Basic | Advanced | Advanced + Slack |
|
Support
|
Community | Email · 24h | Email · 12h | Email · 4h |
Everything you need to know about Token Plan pricing and CLI access.
ANTHROPIC_API_KEY, GEMINI_API_KEY, and OPENAI_API_KEY env vars and Token Factory routes each request to the right model automatically.