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.

MoonshotAI: Kimi K3$15.19
Qwen: Qwen3.6 Flash$1.31

Lowest bill: Qwen: Qwen3.6 Flash · $1.31

Add another

Search by name, then add up to four.

MoonshotAI: Kimi K3Qwen: Qwen3.6 Flash
ProviderMoonshot AIAlibaba
Modalitytext, image, videotext, image, video
Context1.0M1M
Input$0.192/1M$0.1875/1M
Output$15/1M$1.125/1M
Cache read$0.182/1MNot published—
Cache writeNot published—$0.2344/1M
Tiers and extras
MoonshotAI: Kimi K3
—
Qwen: Qwen3.6 Flash
Above 256,000 prompt tokens: in $0.75 · out $3 · cache write $0.9375