ChatMistralAIInput

The API key to use.

A list of custom hooks that must follow (req: Request) => Awaitable<Request | void> They are automatically added when a ChatMistralAI instance is created.

Whether to disable streaming.

If streaming is bypassed, then stream() will defer to invoke().

• If true, will always bypass streaming case.
• If false (default), will always use streaming case if available.

Penalizes the repetition of words based on their frequency in the generated text. A higher frequency penalty discourages the model from repeating words that have already appeared frequently in the output, promoting diversity and reducing repetition.

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 max_tokens cannot exceed the model's context length.

The name of the model to use.

Number of completions to return for each request, input tokens are only billed once.

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.

Version of AIMessage output format to store in message content.

AIMessage.contentBlocks will lazily parse the contents of content into a standard format. This flag can be used to additionally store the standard format as the message content, e.g., for serialization purposes.

• "v0": provider-specific format in content (can lazily parse with .contentBlocks)
• "v1": standardized format in content (consistent with .contentBlocks)

You can also set LC_OUTPUT_VERSION as an environment variable to "v1" to enable this by default.

Determines how much the model penalizes the repetition of words or phrases. A higher presence penalty encourages the model to use a wider variety of words and phrases, making the output more diverse and creative.

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. They are automatically added when a ChatMistralAI instance is created.

A list of custom hooks that must follow (res: Response, req: Request) => Awaitable. They are automatically added when a ChatMistralAI instance is created.

Whether to inject a safety prompt before all conversations.

The seed to use for random sampling. If set, different calls will generate deterministic results.

Override the default server URL used by the Mistral SDK.

Whether or not to stream the response.

Whether or not to include token usage in the stream.

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 top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. Should be between 0 and 1.

Override the default server URL used by the Mistral SDK.

The name of the model to use. Alias for model

Whether to inject a safety prompt before all conversations.