Class MistralAiBatchChatModel

java.lang.Object
dev.langchain4j.model.mistralai.MistralAiBatchChatModel
All Implemented Interfaces:
BatchChatModel

@Experimental public final class MistralAiBatchChatModel extends Object implements BatchChatModel
A BatchChatModel for the Mistral Batch API, which processes multiple chat requests asynchronously at 50% of the standard per-token price.

Requests are submitted inline: each ChatRequest is mapped to a request identical to the one MistralAiChatModel would send, so per-request parameters (temperature, tools, response format, etc.) behave the same in a batch as in a single call. The returned BatchResponse carries the batch id and its current BatchState; results are fetched by retrieve(String) once the job has produced them, preserving submission order.

All requests in a batch run against the single model configured on this batch model (via MistralAiBatchChatModel.Builder.modelName(String)), matching the Mistral constraint of one model per job.

See Also: