Llama 4 models now available via API on Lambda (Maverick/Scout 17B)
https://lambda.ai/inference Llama 4 Scout specs Context window: 1 million tokens Quantization: FP8 Price per 1M input tokens: $0.10 Price per 1M output tokens: $0.30 Llama 4 Maverick specs Context window: 1 million tokens Quantization: FP8 Price per…