Lambda

This host has discontinued its inference service. Its offerings are excluded from current prices and comparisons; price history is kept. Inference API wound down. lambda.ai/inference (checked 2026-10-04): "As the Inference API winds down, you can continue deploying and scaling models seamlessly on NVIDIA GPU instances." No end date is published, so none is recorded. LiteLLM still lists lambda_ai/* prices; they are not live.

Price history

Blended ($/Mtok, 75% input / 25% output) price over time for every model this host serves. Click a legend entry to hide or show its line.

Hosted offerings

ModelVariantInput $/MtokOutput $/MtokConfidence
eu.meta.llama3-2-3b-instruct-v1:0–$0.0150$0.0250medium
Llama 3.1 8B Instruct–$0.0250$0.0400medium
Llama 4 Maverick–$0.0500$0.10medium
Llama 4 Scout–$0.0500$0.10medium
Qwen3 32B–$0.0500$0.10medium
R1 0528–$0.20$0.60medium
DeepSeek V3 0324–$0.20$0.60medium