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.

@cf/mistral/mistral-7b-instruct-v0.1$0.30
DeepSeek: DeepSeek Pro Latest$4.10

Lowest bill: @cf/mistral/mistral-7b-instruct-v0.1 · $0.30

Add another

Search by name, then add up to four.

@cf/mistral/mistral-7b-instruct-v0.1DeepSeek: DeepSeek Pro Latest
ProviderCloudflareDeepSeek
Modalitytexttext
Context—1.0M
Input$0.11/1M$0.1035/1M
Output$0.19/1M$4/1M
Cache readNot published—$0.1/1M