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: Qwen3.6 35B A3B$1.00
Arize AI Qwen 2 1.5B Instruct$0.20

Lowest bill: Arize AI Qwen 2 1.5B Instruct · $0.20

Add another

Search by name, then add up to four.

Qwen: Qwen3.6 35B A3BArize AI Qwen 2 1.5B Instruct
ProviderAlibabaTogether
Modalitytext, image, videotext
Context262K33K
Input$0.1/1M$0.1/1M
Output$0.9/1M$0.1/1M
Cache read$0.025/1MNot published—