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.

MoonshotAI: Kimi K2 Thinking$3.10
Deepseek V3.1 NVFP4$2.30

Lowest bill: Deepseek V3.1 NVFP4 · $2.30

Add another

Search by name, then add up to four.

MoonshotAI: Kimi K2 ThinkingDeepseek V3.1 NVFP4
ProviderMoonshot AITogether
Modalitytexttext
Context262K131K
Input$0.6/1M$0.6/1M
Output$2.5/1M$1.7/1M
Cache read$0.15/1MNot published—