Third Culture cheap tier: near-zero-cost, fast model for bulk classification, extraction, and short summaries. Primary: GLM-5.3-Flash on GMI; fallbacks: DeepSeek V4-Flash on Bitdeer and W&B, Llama 4 Maverick on DeepInfra, Gemini 3.1 Flash Lite on Google AI Studio.
LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.