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 Guard 4 12B$0.36
Qwen: Qwen3.6 Flash$1.31

Lowest bill: Meta: Llama Guard 4 12B · $0.36

Add another

Search by name, then add up to four.

Meta: Llama Guard 4 12BQwen: Qwen3.6 Flash
ProviderMetaAlibaba
Modalityimage, texttext, image, video
Context164K1M
Input$0.18/1M$0.1875/1M
Output$0.18/1M$1.125/1M
Cache writeNot published—$0.2344/1M
Tiers and extras
Meta: Llama Guard 4 12B
—
Qwen: Qwen3.6 Flash
Above 256,000 prompt tokens: in $0.75 · out $3 · cache write $0.9375