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.

Gemma-2 Instruct (27B)$1.60
Amazon: Titan Multimodal Embeddings G1$0.80

Lowest bill: Amazon: Titan Multimodal Embeddings G1 · $0.80

Add another

Search by name, then add up to four.

Gemma-2 Instruct (27B)Amazon: Titan Multimodal Embeddings G1
ProviderTogetherAmazon
Modalitytexttext, image
Context8K128
Input$0.8/1M$0.8/1M
Output$0.8/1M$0/1M
Tiers and extras
Gemma-2 Instruct (27B)
—
Amazon: Titan Multimodal Embeddings G1
Image input: $60 per 1M tokens