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.

Tencent: Hy4 preview$3.34
Macaron V1 Venti$3.30

Lowest bill: Macaron V1 Venti · $3.30

Add another

Search by name, then add up to four.

Tencent: Hy4 previewMacaron V1 Venti
ProviderTencentNovita
Modalitytexttext
Context1.0M1.0M
Input$0.834/1M$0.825/1M
Output$2.501/1M$2.475/1M
Cache read$0.042/1M$0.165/1M
Tiers and extras
Tencent: Hy4 preview
Tier: in $0.834 · out $2.501 · cache read $0.042; Tier: in $0.7506 · out $2.251 · cache read $0.0378
Macaron V1 Venti
—