Fast inference API for 200+ open-source models with pay-per-token pricing
| Tier | Price | Includes | Overage |
|---|---|---|---|
|
Free
free
|
Free
|
Free Credits: 25
|
— |
|
Pay As You Go
usage based
|
Free
|
— |
Llama 3.3 70B input: $0.88/1,000,000 per tokens
Llama 3.3 70B output: $0.88/1,000,000 per tokens
DeepSeek-R1 input: $3/1,000,000 per tokens
DeepSeek-R1 output: $7/1,000,000 per tokens
|