Public catalog

Models for every workflow

Compare the models available through Infra, with transparent token pricing and performance details.

Model pricing
Model Context Input Output Cached input Latency
deepseek-v4.1-flash-1017 1,048,576 tokens $0.345 $1.38 $0.172 310 ms
glm-5.3-flash 1,048,576 tokens $0.172 $0.575 $0.086 379 ms