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 Sol Latest$12.00
Claude Sonnet 5$12.00

Lowest bill: OpenAI: GPT Sol Latest · $12.00

Add another

Search by name, then add up to four.

OpenAI: GPT Sol LatestClaude Sonnet 5
ProviderOpenAIAtlasCloud
Modalitytext, imagetext, image
Context1.1M1M
Input$2/1M$2/1M
Output$10/1M$10/1M
Cache read$0.1/1M$0.2/1M
Cache write$2.5/1MNot published—
Tiers and extras
OpenAI: GPT Sol Latest
Web search: $0.01 per request; Above 272,000 prompt tokens: in $4 · out $15 · cache read $0.2 · cache write $5
Claude Sonnet 5
—