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 Haiku 4.5 (batch)$3.00
deepseek-ai/DeepSeek-R1-0528$2.65

Lowest bill: deepseek-ai/DeepSeek-R1-0528 · $2.65

Add another

Search by name, then add up to four.

Anthropic: Claude Haiku 4.5 (batch)deepseek-ai/DeepSeek-R1-0528
ProviderAnthropicDeepInfra
Modalitytext, imagetext
Context200K164K
Input$0.5/1M$0.5/1M
Output$2.5/1M$2.15/1M
Cache read$0.05/1M$0.35/1M
Cache write$0.625/1MNot published—
1-hour cache write$1/1MNot published—
Tiers and extras
Anthropic: Claude Haiku 4.5 (batch)
Web search: $0.01 per request
deepseek-ai/DeepSeek-R1-0528
—