API pricing
Pay for the tokens you use. Credits never expire.
Estimate your cost
Model
Count cached tokens separately from uncached input.
Estimated total
415.065 credits
Rates per 1M tokens
- Input
- $0.0798
- Output
- $0.16065
- Cache read
- Not published
- Cache write · 5 min
- Not published
Based on published token rates. Check Activity for the final charge.
| Model | Offer |
|---|---|
| Ling 3.1 Flash (Free) No token charge | Free |
| Laguna S 2.1 Free No token charge | Free |
| Gemini 3.6 and 3.7 Flash Through December 31, 2026 | 50% off |
| Gemini 3.8 Flash Through December 31, 2026 | 50% off |
Funding & fees
Billing docs- Crypto deposits
- 0% AI Pass fee
Credits match the USDC received. Network and swap costs are separate.
- Credit balance
- $1 = 1,000 credits
Credits stay on your key until you use them.
- Web fetch
- $0.001 per successful fetch
Platform fee, plus model tokens. Failed, blocked and timed-out fetches have no fetch fee. Redirects count once.
- Other server tools
- $0.01 per web search · datetime free
Model tokens are billed separately.
- Routing markup
- Auto 8% · Fusion 10%
Total markups over provider cost, included in published rates. Fusion includes classification.