DeepSeek: DeepSeek V4.1 Flash (batch)

DeepSeek V4.1 Flash (batch) is a DeepSeek model that accepts text and image input, with a context window of 1,048,576 tokens and up to 131,072 completion tokens per response. It supports tool calling and reasoning, which suits multi-step tasks and tool-driven workflows over long inputs. Structured output support and open-weights status are not listed, so confirm both before relying on them. Pricing is $0.112 per million input tokens and $0.336 per million output tokens, a low price point for high-volume work. Its blended benchmark score of 66.3 comes from a single independent benchmark (AI Index score of 65.1), so its relative standing is thinly evidenced. Teams processing large volumes of long-context text or images on a tight budget should shortlist it. They should run their own evaluations before moving quality-sensitive workloads onto it.