Model Pricing
All prices in USD per million tokens
| Model | Input (SpareAPI) | Output (SpareAPI) | Input (Official) | Output (Official) | Savings |
|---|---|---|---|---|---|
| Claude Opus 4.6 | $3.00 | $15.00 | $15.00 | $75.00 | Save 80% |
| Claude Sonnet 4.6 | $0.60 | $3.00 | $3.00 | $15.00 | Save 80% |
| Claude Haiku 4.5 | $0.16 | $0.80 | $0.80 | $4.00 | Save 80% |
| GPT-5 | $1.00 | $3.00 | $5.00 | $15.00 | Save 80% |
| GPT-5.4 | $0.50 | $2.00 | $2.50 | $10.00 | Save 80% |
| Gemini 2.5 Flash | $0.03 | $0.12 | $0.15 | $0.60 | Save 80% |
| Gemini 2.5 Pro | $0.25 | $2.00 | $1.25 | $10.00 | Save 80% |
Prices update in real-time based on provider availability
How Pricing Works
Pay-Per-Use
No monthly subscriptions. Top up your balance and pay only for the tokens you use. Start with as little as $1.
Dynamic Pricing
Prices are set by providers competing on the network. More providers = lower prices. You always get the best available rate.
No Hidden Fees
The price you see is the price you pay. No markup on top of provider rates. No minimum commitments.
FAQ
How much does it cost?
All SpareAPI prices are fixed at 20% of official API prices (二折). You save 80% on every call — across Claude, GPT, and Gemini models.
Is there a minimum top-up?
The minimum top-up is $1. There are no monthly fees or minimum commitments.
How is usage calculated?
Usage is calculated per token, just like the official APIs. Input tokens (your prompts) and output tokens (model responses) are priced separately.
What happens if a request fails?
Failed requests are not charged. If a provider goes offline mid-request, we automatically retry with another provider.
Can I set a spending limit?
Yes, your spending is limited by your balance. You can only use what you've topped up. We never charge more than your balance.
Do you support streaming?
Yes, all endpoints support streaming responses, just like the official APIs.