Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.magnitude.dev/llms.txt

Use this file to discover all available pages before exploring further.

Magnitude is pay-as-you-go. We pass through the underlying API cost of each model with no markup. You pay what we pay. Sign up at app.magnitude.dev and you get $5 of free credits to start, no card required.
Want to chat about your use case for open models? Book a call with our founder →

​
How it works

  • Free to start. $5 of credits on signup. Never expires.
  • Pass-through pricing. Each request is charged at the model’s actual per-token cost. No markup, no subscription, no rate-limit windows.
  • Top-ups. Add credits in multiples of $5 (presets at $10, $20, $50, custom up to $500). Stripe processing fees are passed through as a separate line item.
  • Auto-reload (optional). Off by default. Turn it on and set a threshold, top-up amount, and monthly cap. When your balance drops below the threshold, we charge your card for the configured amount.
Manage all of this on the billing page in the console.

​
Per-token pricing

Pricing per 1M tokens, identical to what the underlying provider charges us.
ModelInputCached inputOutput
Kimi K2.5$0.60$0.10$3.00
Kimi K2.6$0.95$0.16$4.00
GLM 5.1$1.40$0.26$4.40
Roughly 90% of input tokens are served from cache after the first turn of a conversation, so real-world cost is closer to the cached input column than the input column.

​
Models in the lineup

The current lineup of models powering the agent team:
  • Kimi K2.5
  • Kimi K2.6
  • GLM 5.1
Each model is assigned to the agent it performs best for. See Agent Team for the full mapping.

​
Checking your balance

Run /usage in the CLI to see your current balance, recent spend, top-up history, and auto-reload status.