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.

Upstage: Solar Decide$0.05
Anthropic: Claude Haiku 5.5 (batch)$0.30

Lowest bill: Upstage: Solar Decide · $0.05

Add another

Search by name, then add up to four.

Upstage: Solar DecideAnthropic: Claude Haiku 5.5 (batch)
ProviderUpstageAnthropic
Modalitytexttext, image
Context524K1M
Input$0.05/1M$0.05/1M
Output$0/1M$0.25/1M
Cache read$0.05/1M$0.005/1M
Cache writeNot published—$0.0625/1M
1-hour cache writeNot published—$0.1/1M
Tiers and extras
Upstage: Solar Decide
—
Anthropic: Claude Haiku 5.5 (batch)
Web search: $0.01 per request; Above 100,000 prompt tokens: in $0.25 · out $1.25 · cache read $0.025 · cache write $0.3125 · 1h cache write $0.5