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 Chat Latest$35.00
Anthropic: Claude Opus 4.5$30.00

Lowest bill: Anthropic: Claude Opus 4.5 · $30.00

Add another

Search by name, then add up to four.

OpenAI: GPT Chat LatestAnthropic: Claude Opus 4.5
ProviderOpenAIAnthropic
Modalitytext, imagetext, image
Context400K200K
Input$5/1M$5/1M
Output$30/1M$25/1M
Cache read$0.5/1M$0.5/1M
Cache writeNot published—$6.25/1M
1-hour cache writeNot published—$10/1M
Tiers and extras
OpenAI: GPT Chat Latest
Web search: $0.01 per request
Anthropic: Claude Opus 4.5
Web search: $0.01 per request