interface MistralAIInputThe API key to use.
Batch size to use when passing multiple documents to generate
A list of custom hooks that must follow (req: Request) => Awaitable<Request | void> They are automatically added when a ChatMistralAI instance is created
Optional custom HTTP client to manage API requests Allows users to add custom fetch implementations, hooks, as well as error and response processing.
The maximum number of concurrent calls that can be made.
Defaults to Infinity, which means no limit.
The maximum number of retries that can be made for a single call, with an exponential backoff between each attempt. Defaults to 6.
The maximum number of tokens to generate in the completion. The token count of your prompt plus maxTokens cannot exceed the model's context length.
The name of the model to use.
Custom handler to handle failed attempts. Takes the originally thrown error object as input, and should itself throw an error if the input error is not retryable.
The seed to use for random sampling. If set, different calls will generate deterministic results.
Alias for seed
A list of custom hooks that must follow (err: unknown, req: Request) => Awaitable
A list of custom hooks that must follow (res: Response, req: Request) => Awaitable
Override the default server URL used by the Mistral SDK.
Whether or not to stream the response.
What sampling temperature to use, between 0.0 and 2.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
Nucleus sampling, where the model considers the results of the tokens with topP probability mass.
So 0.1 means only the tokens comprising the top 10% probability mass are considered.
Should be between 0 and 1.
Whether to use the Fill-In-Middle (FIM) API for code completion.
When true, uses client.fim.complete() / client.fim.stream().
When false, uses client.chat.complete() / client.chat.stream() with the prompt wrapped as a user message.
FIM is only supported for code models like codestral-latest.
For general-purpose models like mistral-large-latest, set this to false.
Override the default server URL used by the Mistral SDK.