Skip to main content

Changelog

This is the list of changes to the Mistral API.
November 6, 2029

  • We released moderation API and batch API.
  • We introduced three new parameters:
    • presence_penalty: penalizes the repetition of words or phrases
    • frequency_penalty: penalizes the repetition of words based on their frequency in the generated text
    • n: number of completions to return for each request, input tokens are only billed once.

October 9, 2024

  • We released Ministral 3B (ministral-3b-2410) and Ministral 8B (ministral-8b-2410).

September 17, 2024

  • We released Pixtral (pixtral-12b-2409) and Mistral Small v24.09 (mistral-small-2409).
  • We reduced price on our flagship model, Mistral Large 2.
  • We introduced a free API tier on La Plateforme.

September 13, 2024

  • In le Chat, we added a mitigation against an obfuscated prompt method that could lead to data exfiltration, reported by researchers Xiaohan Fu and Earlence Fernandes. The attack required users to willingfully copy and paste adversarial prompts and provide personal data to the model. No user was impacted and no data was exfiltrated.

July 29, 2024

  • We released version 1.0 of our Python and JS SDKs with major upgrades and syntax changes. Check out our migration guide for details.
  • We released Agents API. See details here.

July 24, 2024

  • We released Mistral Large 2 (mistral-large-2407).
  • We added fine-tuning support for Codestral, Mistral Nemo and Mistral Large. Now the model choices for fine-tuning are open-mistral-7b (v0.3), mistral-small-latest (mistral-small-2402), codestral-latest (codestral-2405), open-mistral-nemo and , mistral-large-latest (mistral-large-2407)

July 18, 2024

  • We released Mistral Nemo (open-mistral-nemo).

July 16, 2024

  • We released Codestral Mamba (open-codestral-mamba) and Mathstral.

Jun 5, 2024

May 29, 2024

  • New model available: codestral-latest (aka codestral-2405). Check out the code generation docs.

May 23, 2024

  • Function calling: tool_call_id is now mandatory in chat messages with the tool role.

Apr. 17, 2024

  • New model available: open-mixtral-8x22b (aka open-mixtral-8x22b-2404). Check the release blog for details.
  • For function calling, tool_call_id must not be null for open-mixtral-8x22b.
  • We released three versions of tokenizers for commercial and open-weight models: check the related guide and repo for more details.

Mar. 28, 2024

  • JSON mode now available for all models on La Plateforme.

Feb. 26, 2024

  • API endpoints: We renamed 3 API endpoints and added 2 model endpoints.

    • open-mistral-7b (aka mistral-tiny-2312): renamed from mistral-tiny. The endpoint mistral-tiny will be deprecated in three months.
    • open-mixtral-8x7B (aka mistral-small-2312): renamed from mistral-small. The endpoint mistral-small will be deprecated in three months.
    • mistral-small-latest (aka mistral-small-2402): new model.
    • mistral-medium-latest (aka mistral-medium-2312): old model. The previous mistral-medium has been dated and tagged as mistral-medium-2312. The endpoint mistral-medium will be deprecated in three months.
    • mistral-large-latest (aka mistral-large-2402): our new flagship model with leading performance.

  • New API capabilities:

  • La Plateforme:

    • We added multiple currency support to the payment system, including the option to pay in US dollars.
    • We introduced enterprise platform features including admin management, which allows users to manage individuals from your organization.

  • Le Chat:

    • We introduced the brand new chat interface Le Chat to easily interact with Mistral models.
    • You can currently interact with three models: Mistral Large, Mistral Next, and Mistral Small.

Jan. 11, 2024

  • We have enhanced the API's strictness. Previously the API would silently ignores unsupported parameters in the requests, but it now strictly enforces the validity of all parameters. If you have unsupported parameters in your request, you will see the error message "Extra inputs are not permitted".
  • A previous version of the guardrailing documentation incorrectly referred to the API parameter as safe_mode instead of safe_prompt. We corrected this in the documentation.

Jan. 16, 2024

  • We added token usage information in streaming requests. You can find it in the last chunk returned.