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.

Llama 4 Scout 17B$0.83
Qwen3.5 9B FP8$0.42

Lowest bill: Qwen3.5 9B FP8 · $0.42

Add another

Search by name, then add up to four.

Llama 4 Scout 17BQwen3.5 9B FP8
ProviderAmazon BedrockTogether
Modalitytexttext
Context—262K
Input$0.17/1M$0.17/1M
Output$0.66/1M$0.25/1M