Provider model catalog
Lambda models
GPU cloud and inference for AI workloads
20 unique catalog models
Model pricing and capabilities
- deepseek-llama3.3-70b$0.200 / 1M tokens input
- deepseek-r1-0528$0.200 / 1M tokens input
- deepseek-r1-671b$0.800 / 1M tokens input
- deepseek-v3-0324$0.200 / 1M tokens input
- hermes3-405b$0.800 / 1M tokens input
- hermes3-70b$0.120 / 1M tokens input
- hermes3-8b$0.025 / 1M tokens input
- lfm-40b$0.100 / 1M tokens input
- lfm-7b$0.025 / 1M tokens input
- llama-4-maverick-17b-128e-instruct-fp8$0.050 / 1M tokens input
- llama-4-scout-17b-16e-instruct$0.050 / 1M tokens input
- llama3.1-405b-instruct-fp8$0.800 / 1M tokens input
- llama3.1-70b-instruct-fp8$0.120 / 1M tokens input
- llama3.1-8b-instruct$0.025 / 1M tokens input
- llama3.1-nemotron-70b-instruct-fp8$0.120 / 1M tokens input
- llama3.2-11b-vision-instruct$0.015 / 1M tokens input
- llama3.2-3b-instruct$0.015 / 1M tokens input
- llama3.3-70b-instruct-fp8$0.120 / 1M tokens input
- qwen25-coder-32b-instruct$0.050 / 1M tokens input
- qwen3-32b-fp8$0.050 / 1M tokens input