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.

Muse Spark Open 816B A42B$5.50
Google: Gemini 2.5 Pro$11.25

Lowest bill: Muse Spark Open 816B A42B · $5.50

Add another

Search by name, then add up to four.

Muse Spark Open 816B A42BGoogle: Gemini 2.5 Pro
ProviderTogetherGoogle
Modalitytexttext, image, audio, video
Context1.0M1.0M
Input$1.25/1M$1.25/1M
Output$4.25/1M$10/1M
Cache read$0.15/1M$0.125/1M
Cache writeNot published—$0.375/1M
Tiers and extras
Muse Spark Open 816B A42B
—
Google: Gemini 2.5 Pro
Web search: $0.014 per request; Image input: $1.25 per 1M tokens; Audio: $1.25 per 1M tokens; Audio cache: $0.125 per 1M tokens; Reasoning: $10 per 1M tokens; Above 200,000 prompt tokens: in $2.5 · out $15 · cache read $0.25 · audio $2.5