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.

Meta: Llama 3.3 70B Instruct$1.35
Deepseek V3.1 NVFP4$2.30

Lowest bill: Meta: Llama 3.3 70B Instruct · $1.35

Add another

Search by name, then add up to four.

Meta: Llama 3.3 70B InstructDeepseek V3.1 NVFP4
ProviderIo NetTogether
Modalitytexttext
Context128K131K
Input$0.585/1M$0.6/1M
Output$0.768/1M$1.7/1M
Cache read$0.2925/1MNot published—