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.

Anthropic: Claude Opus 4.1 (batch)$45.00
OpenAI: GPT Image 2.5 Sunburst$16.00

Lowest bill: OpenAI: GPT Image 2.5 Sunburst · $16.00

Add another

Search by name, then add up to four.

Anthropic: Claude Opus 4.1 (batch)OpenAI: GPT Image 2.5 Sunburst
ProviderAnthropicOpenAI
Modalityimage, texttext, image
Context200K400K
Input$7.5/1M$8/1M
Output$37.5/1M$8/1M
Cache read$0.75/1M$2/1M
Cache write$9.375/1MNot published—
1-hour cache write$15/1MNot published—
Tiers and extras
Anthropic: Claude Opus 4.1 (batch)
Web search: $0.01 per request
OpenAI: GPT Image 2.5 Sunburst
Web search: $0.01 per request; Image output: $30 per 1M tokens