Integrate multimodal vision capabilities using Qwen3-VL 235B A22B Instruct, designed to process both text and images seamlessly. This model delivers cost-effective pricing at $0.29/1M input and $1.15/1M output tokens, native tool calling support, open weights architecture. Access Qwen3-VL 235B A22B Instruct via the Merge Gateway API with up to 33K output tokens.
Tokens
Tokens
Tokens
Qwen3-VL 235B A22B Instruct by Merge Gateway costs $0.29 per 1M input tokens and $1.15 per 1M output tokens. Cached reads cost $0.16 per 1M tokens.