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 VL 30B A3B Instruct$0.90
Glm 4.5 Air Fp8$1.30

Lowest bill: Qwen: Qwen3 VL 30B A3B Instruct · $0.90

Add another

Search by name, then add up to four.

Qwen: Qwen3 VL 30B A3B InstructGlm 4.5 Air Fp8
ProviderPhalaTogether
Modalitytext, imagetext
Context128K131K
Input$0.2/1M$0.2/1M
Output$0.7/1M$1.1/1M
Cache read$0.03/1MNot published—