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.

DeepSeek: DeepSeek V3$1.29
Qwen: Qwen-Plus$1.04

Lowest bill: Qwen: Qwen-Plus · $1.04

Add another

Search by name, then add up to four.

DeepSeek: DeepSeek V3Qwen: Qwen-Plus
ProviderDeepSeekAlibaba
Modalitytexttext
Context164K1M
Input$0.2574/1M$0.26/1M
Output$1.029/1M$0.78/1M
Cache readNot published—$0.052/1M
Cache writeNot published—$0.325/1M
Tiers and extras
DeepSeek: DeepSeek V3
—
Qwen: Qwen-Plus
Above 256,000 prompt tokens: in $0.78 · out $2.34 · cache read $0.156 · cache write $0.975