theserverless.dev InferenceList

Compare

Add up to four models. The bill starts at 1M input tokens, 1M output tokens, and 1,000 units.

Monthly bill

Token models use the token counts. Other models use units times the flat rate.

Qwen: Qwen3.7 Max$5.90
Llama 3 70B Euryale V2.1$2.96

Lowest bill: Llama 3 70B Euryale V2.1 · $2.96

Add another

Search by name, then add up to four.

Qwen: Qwen3.7 MaxLlama 3 70B Euryale V2.1
ProviderAlibabaNovita
Modalitytexttext
Context1M8K
Input$1.475/1M$1.48/1M
Output$4.425/1M$1.48/1M
Cache read$0.295/1MNot published—
Cache write$1.844/1MNot published—