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.

Qwen: Qwen3.5 Plus 2026-04-20$2.10
Amazon: Nova 2 Lite$2.80

Lowest bill: Qwen: Qwen3.5 Plus 2026-04-20 · $2.10

Add another

Search by name, then add up to four.

Qwen: Qwen3.5 Plus 2026-04-20Amazon: Nova 2 Lite
ProviderAlibabaAmazon
Modalitytext, image, videotext, image, video
Context1M1M
Input$0.3/1M$0.3/1M
Output$1.8/1M$2.5/1M
Cache write$0.375/1MNot published—
Tiers and extras
Qwen: Qwen3.5 Plus 2026-04-20
Above 256,000 prompt tokens: in $0.375 · out $2.25 · cache write $0.4688
Amazon: Nova 2 Lite
—