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.

OpenAI: GPT-5.4 Pro (batch)$105
Claude Opus 4.1 20250805 Coding$90.00

Lowest bill: Claude Opus 4.1 20250805 Coding · $90.00

Add another

Search by name, then add up to four.

OpenAI: GPT-5.4 Pro (batch)Claude Opus 4.1 20250805 Coding
ProviderOpenAIAtlasCloud
Modalitytext, imagetext
Context1.1M200K
Input$15/1M$15/1M
Output$90/1M$75/1M
Cache readNot published—$1.5/1M
Tiers and extras
OpenAI: GPT-5.4 Pro (batch)
Web search: $0.01 per request; Above 272,000 prompt tokens: in $30 · out $135
Claude Opus 4.1 20250805 Coding
—