Pricing
211API is pay-as-you-go: pay only for what you use. All channel multipliers are public — billed as low as 5% of official list price.
How billing works
Cost = actual token usage × model list price × channel multiplier- Pay as you go — No subscription, no minimum spend. Settled per call by actual token usage.
- Public multipliers — Every model's channel multiplier is shown in the console "Models" list, as low as 5% of official list price.
- Per-call tracking — Routing, token usage and multiplier details for every call are visible in the console in real time.
Models by tool
| Tool | Representative model | Positioning |
|---|---|---|
| Claude Code | fable-5 | Coding / review / refactoring |
| CodeX | gpt-5.6-sol | Complex reasoning & long tasks |
| CodeX | gpt-5.6-luna | High-frequency light calls, lower multiplier |
| Gemini CLI | See console model list | High-frequency, low-latency light workloads |
Note
Model lists, channel multipliers and balances follow the live data in the 211API console. Switching models only requires changing the model name in your config — key and endpoint stay the same.
Tips for controlling costs
- Prefer low-multiplier models (e.g.
gpt-5.6-luna) for high-frequency, light requests. - Set a quota cap on your key in the console to prevent unexpected spend.
- Review usage details regularly in the console and optimize call patterns per tool and model.