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.

Nova Pro$200
Glm 4.5 Air Fp8$1.30

Lowest bill: Glm 4.5 Air Fp8 · $1.30

Add another

Search by name, then add up to four.

Nova ProGlm 4.5 Air Fp8
ProviderAmazon BedrockTogether
Modalitytexttext
Context—131K
Input$0.2/tokens cache read$0.2/1M
OutputNot published—$1.1/1M
Cache read$0.2/1MNot published—