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.

Beam 1.0 501B A23B$1.60
Meta: Llama 3.1 70B Instruct$0.80

Lowest bill: Meta: Llama 3.1 70B Instruct · $0.80

Add another

Search by name, then add up to four.

Beam 1.0 501B A23BMeta: Llama 3.1 70B Instruct
ProviderTogetherMeta
Modalitytexttext
Context1.0M131K
Input$0.4/1M$0.4/1M
Output$1.2/1M$0.4/1M
Cache read$0.04/1MNot published—