bge-m3 and Qwen3 VL 30B A3B Instruct are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
bge-m3, from baai, has a 8,194-token context window and is priced at $0.01/M tokens on OpenRouter.
Qwen3 VL 30B A3B Instruct, from Qwen, has a 262,144-token context window and is priced at $0.13/M tokens input, $0.52/M tokens output on OpenRouter.