Meter Documentation
Introduction
Meter is the first consumer AI product with postpaid billing. No subscription. No credits. Use any model, pay only for what you use. Run multi-model debates to get the best answer.
Every top frontier model available — Claude, GPT, Gemini, Grok, DeepSeek. One bill. No complexity.
How It Works
- Create an account with a passkey
- Add a card — no charge, just a verification hold
- Start chatting — every model is available
- Each response shows:
Model · Tokens · $Cost · Status - Your card is charged when your balance reaches the threshold, or monthly — whichever comes first
Pay Per Use
Every message has a cost based on the model used and tokens consumed. Below each response you see:
Model name. Token count. Cost in dollars. Settlement status.
Pricing
Pay-per-token pricing.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Sonnet 4.6 | $6.00 | $30.00 |
| Opus 4.6 | $10.00 | $50.00 |
| GPT-5.4 | $5.00 | $30.00 |
| Gemini 3.1 Pro | $4.00 | $24.00 |
| Grok 4.1 Fast | $0.40 | $1.00 |
| DeepSeek V3 | $0.54 | $2.20 |
| Meter 1.0 (Debate) | $6.00 | $30.00 |
The daily meter in the header shows your running total. Set a daily spending cap in settings.
Debate mode runs your question through multiple models simultaneously, then synthesizes the best answer. Standard per-token pricing applies.
Billing
Your card is charged when your balance reaches the threshold, or at the end of each month — whichever comes first. All payments are processed securely.
Models
Every frontier model available through one interface. Quality measured by GPQA Diamond (graduate-level science accuracy). Speed is output tokens per second from native APIs.
| Model | Provider | GPQA | Speed |
|---|---|---|---|
| Sonnet 4.6 | Anthropic | 74% | 60 tok/s |
| Opus 4.6 | Anthropic | 91% | 70 tok/s |
| GPT-5.4 | OpenAI | 92% | 90 tok/s |
| Gemini 3.1 Pro | 92% | 138 tok/s | |
| Grok 4.1 Fast | xAI | 86% | 129 tok/s |
| DeepSeek V3 | DeepSeek | 59% | 50 tok/s |
| Meter 1.0 (Debate) | Meter | 93% | 30 tok/s |
Meter 1.0 runs your question through multiple frontier models simultaneously, then synthesizes the best answer. Higher quality, competitive pricing.
MCP
Connect your coding agent to your Meter decisions, blueprints, and debates. The Meter MCP server gives any MCP-compatible IDE direct access to your thinking.
Available Tools
| Tool | Description |
|---|---|
| get_decisions | List and search your decisions log |
| get_decision | Fetch full detail of a single decision |
| get_blueprints | List and search your blueprints |
| get_blueprint | Fetch full content of a blueprint |
| get_debates | List debate summaries with synthesis |
| search | Full-text search across all artifact types |
Setup
Get your API key from Settings → API on meter.chat, then configure your editor:
Run in your terminal
claude mcp add meter --transport http https://meter.chat/api/mcp -H "Authorization: Bearer your-api-key"
View on GitHub — MIT licensed, contributions welcome.