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: Hy3$0.66
deepseek-v4-flash-0731$0.39

Lowest bill: deepseek-v4-flash-0731 · $0.39

Add another

Search by name, then add up to four.

Tencent: Hy3deepseek-v4-flash-0731
ProviderTencentVenice
Modalitytexttext
Context262K1M
Input$0.132/1M$0.13/1M
Output$0.528/1M$0.26/1M
Cache read$0.033/1M$0.028/1M
Tiers and extras
Tencent: Hy3
Tier: in $0.132 · out $0.528 · cache read $0.033; Tier: in $0.0825 · out $0.33 · cache read $0.0206
deepseek-v4-flash-0731
—