mistralai · Bam4d · Jan 13, 2025 · Jan 13, 2025
diff --git a/docs/getting-started/changelog.mdx b/docs/getting-started/changelog.mdx
@@ -3,6 +3,8 @@ id: changelog
 title: Changelog
 sidebar_position: 1.8
 ---
+January 13, 2025
+- We released Codestral 25.01 (`codestral-2501`).
 
 November 18, 2024
 - We released Mistral Large 24.11 (`mistral-large-2411`) and Pixtral Large (`pixtral-large-2411`). 

diff --git a/docs/getting-started/introduction.mdx b/docs/getting-started/introduction.mdx
@@ -16,20 +16,18 @@ We release both premier models and free models, driving innovation and convenien
 
 - Mistral Large, our top-tier reasoning model for high-complexity tasks with the lastest version released [November 2024](https://mistral.ai/news/pixtral-large/)
 - Pixtral Large, our frontier-class multimodal model released [November 2024](https://mistral.ai/news/pixtral-large/)
-- Ministral 3B, world’s best edge model released [October 2024](https://mistral.ai/news/ministraux/).
-- Ministral 8B, powerful edge model with extremely high performance/price ratio released [October 2024](https://mistral.ai/news/ministraux/).
-- Mistral Small, our latest enterprise-grade small model with the lastest version v2 released [September 2024](https://mistral.ai/news/september-24-release/).
-- Codestral, our cutting-edge language model for coding released [May 2024](https://mistral.ai/news/codestral/)
+- Ministral 3B, world’s best edge model released [October 2024](https://mistral.ai/news/ministraux/)
+- Ministral 8B, powerful edge model with extremely high performance/price ratio released [October 2024](https://mistral.ai/news/ministraux/)
+- Mistral Small, our latest enterprise-grade small model with the lastest version v2 released [September 2024](https://mistral.ai/news/september-24-release/)
+- Codestral, our cutting-edge language model for coding with the latest version released January 2025
 - Mistral Embed, our state-of-the-art semantic for extracting representation of text extracts
+- Mistral Moderation, our moderation service that enables our users to detect harmful text content
 
 ### Free models
 - Pixtral, a 12B model with image understanding capabilities in addition to text released [September 2024](https://mistral.ai/news/pixtral-12b/)
 - Mistral NeMo, our best multilingual open source model released [July 2024](https://mistral.ai/news/mistral-nemo/)
 - Codestral Mamba, our first mamba 2 open source model released [July 2024](https://mistral.ai/news/codestral-mamba/)
 - Mathstral 7b, our first math open source model released [July 2024](https://mistral.ai/news/mathstral/)
-- Mixtral 8x22b, our best open source model to date released [April 2024](https://mistral.ai/news/mixtral-8x22b/)
-- Mixtral 8x7b, our first sparse mixture-of-experts released [December 2023](https://mistral.ai/news/mixtral-of-experts/)
-- Mistral 7b, our first dense model released [September 2023](https://mistral.ai/news/announcing-mistral-7b/)
 
 Learn more about our models [here](/getting-started/models/models_overview).
 

diff --git a/docs/getting-started/models/benchmark.md b/docs/getting-started/models/benchmark.md
@@ -15,7 +15,7 @@ You can find the benchmark results in the following blog posts:
 - [Mistral Large](https://mistral.ai/news/mistral-large-2407/): a cutting-edge text generation model with top-tier reasoning capabilities.
 It can be used for complex multilingual reasoning tasks, including text understanding, transformation, and code generation.
 - [Mistral Nemo](https://mistral.ai/news/mistral-nemo/): Mistral Nemo's reasoning, world knowledge, and coding performance are state-of-the-art in its size category.  As it relies on standard architecture, Mistral Nemo is easy to use and a drop-in replacement in any system using Mistral 7B that it supersedes.
-- [Codestral](https://mistral.ai/news/codestral/): as a 22B model, Codestral sets a new standard on the performance/latency space for code generation compared to previous models used for coding.
+- [Codestral](https://mistral.ai/news/codestral-2501/): Codestral sets a new standard on the performance/latency space for code generation compared to previous models used for coding.
 - [Codestral-Mamba](https://mistral.ai/news/codestral-mamba/): we have trained this model with advanced code and reasoning capabilities, enabling the model to have a strong performance on par with SOTA transformer-based models.
 - [Mathstral](https://mistral.ai/news/mathstral/): Mathstral stands on the shoulders of Mistral 7B and specialises in STEM subjects. It achieves state-of-the-art reasoning capacities in its size category across various industry-standard benchmarks. 
 - [Mixtral 8x22B](https://mistral.ai/news/mixtral-8x22b/): our most performant open model. It handles English,

diff --git a/docs/getting-started/models/overview.md b/docs/getting-started/models/overview.md
@@ -16,12 +16,12 @@ Mistral provides two types of models: free models and premier models.
 
 | Model               | Weight availability|Available via API| Description | Max Tokens| API Endpoints|Version|
 |--------------------|:--------------------:|:--------------------:|:--------------------:|:--------------------:|:--------------------:|:--------------------:|
-| Mistral Large  |:heavy_check_mark: <br/> [Mistral Research License](https://mistral.ai/licenses/MRL-0.1.md)| :heavy_check_mark: |Our top-tier reasoning model for high-complexity tasks with the lastest version released November 2024. Learn more on our [blog post](https://mistral.ai/news/pixtral-large/) | 128k   | `mistral-large-latest`| 24.11|
-| Pixtral Large  |:heavy_check_mark: <br/> [Mistral Research License](https://mistral.ai/licenses/MRL-0.1.md)| :heavy_check_mark: |Our frontier-class multimodal model released November 2024. Learn more on our [blog post](https://mistral.ai/news/pixtral-large/)| 128k   | `pixtral-large-latest`| 24.11|
-| Ministral 3B | | :heavy_check_mark: | World’s best edge model. Learn more on our [blog post](https://mistral.ai/news/ministraux/) | 128k  | `ministral-3b-latest` | 24.10|
-| Ministral 8B | :heavy_check_mark: <br/> [Mistral Research License](https://mistral.ai/licenses/MRL-0.1.md)| :heavy_check_mark: |Powerful edge model with extremely high performance/price ratio. Learn more on our [blog post](https://mistral.ai/news/ministraux/) | 128k  | `ministral-8b-latest` | 24.10|
+| Codestral | | :heavy_check_mark: | Our cutting-edge language model for coding with the second version released January 2025, Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Learn more on our blog post(https://mistral.ai/news/codestral-2501/) | 256k  | `codestral-latest` | 25.01|
+| Mistral Large  |:heavy_check_mark: <br/> [Mistral Research License](https://mistral.ai/licenses/MRL-0.1.md)| :heavy_check_mark: |Our top-tier reasoning model for high-complexity tasks with the lastest version released November 2024. Learn more on our [blog post](https://mistral.ai/news/pixtral-large/) | 131k   | `mistral-large-latest`| 24.11|
+| Pixtral Large  |:heavy_check_mark: <br/> [Mistral Research License](https://mistral.ai/licenses/MRL-0.1.md)| :heavy_check_mark: |Our frontier-class multimodal model released November 2024. Learn more on our [blog post](https://mistral.ai/news/pixtral-large/)| 131k   | `pixtral-large-latest`| 24.11|
+| Ministral 3B | | :heavy_check_mark: | World’s best edge model. Learn more on our [blog post](https://mistral.ai/news/ministraux/) | 131k  | `ministral-3b-latest` | 24.10|
+| Ministral 8B | :heavy_check_mark: <br/> [Mistral Research License](https://mistral.ai/licenses/MRL-0.1.md)| :heavy_check_mark: |Powerful edge model with extremely high performance/price ratio. Learn more on our [blog post](https://mistral.ai/news/ministraux/) | 131k  | `ministral-8b-latest` | 24.10|
 | Mistral Small | :heavy_check_mark: <br/> [Mistral Research License](https://mistral.ai/licenses/MRL-0.1.md) | :heavy_check_mark: | Our latest enterprise-grade small model with the lastest version v2 released September 2024. Learn more on our [blog post](https://mistral.ai/news/september-24-release/) | 32k  | `mistral-small-latest` | 24.09|
-| Codestral |:heavy_check_mark: <br/> [Mistral Non-Production License](https://mistral.ai/licenses/MNPL-0.1.md) | :heavy_check_mark: | Our cutting-edge language model for coding released May 2024 | 32k  | `codestral-latest` | 24.05|
 | Mistral Embed | | :heavy_check_mark: | Our state-of-the-art semantic for extracting representation of text extracts | 8k  | `mistral-embed` | 23.12|
 | Mistral Moderation | | :heavy_check_mark: | Our moderation service that enables our users to detect harmful text content | 8k  | `mistral-moderation-latest` | 24.11|
 
@@ -32,13 +32,13 @@ Mistral provides two types of models: free models and premier models.
 
 | Model               | Weight availability|Available via API| Description | Max Tokens| API Endpoints|Version|
 |--------------------|:--------------------:|:--------------------:|:--------------------:|:--------------------:|:--------------------:|:--------------------:|
-| Pixtral | :heavy_check_mark: <br/> Apache2 | :heavy_check_mark: | A 12B model with image understanding capabilities in addition to text. Learn more on our [blog post](https://mistral.ai/news/pixtral-12b/)| 128k  | `pixtral-12b-2409` | 24.09|
+| Pixtral | :heavy_check_mark: <br/> Apache2 | :heavy_check_mark: | A 12B model with image understanding capabilities in addition to text. Learn more on our [blog post](https://mistral.ai/news/pixtral-12b/)| 131k  | `pixtral-12b-2409` | 24.09|
 
 - **Research models**
 
 | Model               | Weight availability|Available via API| Description | Max Tokens| API Endpoints|Version|
 |--------------------|:--------------------:|:--------------------:|:--------------------:|:--------------------:|:--------------------:|:--------------------:|
-| Mistral Nemo | :heavy_check_mark: <br/> Apache2 | :heavy_check_mark: | Our best multilingual open source model released July 2024. Learn more on our [blog post](https://mistral.ai/news/mistral-nemo/) | 128k  | `open-mistral-nemo`| 24.07|
+| Mistral Nemo | :heavy_check_mark: <br/> Apache2 | :heavy_check_mark: | Our best multilingual open source model released July 2024. Learn more on our [blog post](https://mistral.ai/news/mistral-nemo/) | 131k  | `open-mistral-nemo`| 24.07|
 | Codestral Mamba | :heavy_check_mark: <br/> Apache2 | :heavy_check_mark: | Our first mamba 2 open source model released July 2024. Learn more on our [blog post](https://mistral.ai/news/codestral-mamba/) | 256k  | `open-codestral-mamba`| v0.1|
 | Mathstral | :heavy_check_mark: <br/> Apache2 |  | Our first math open source model released July 2024. Learn more on our [blog post](https://mistral.ai/news/mathstral/) | 32k  | NA| v0.1|
 
@@ -58,7 +58,7 @@ Here are the details of the available versions:
 - `ministral-8b-latest`: currently points to `ministral-8b-2410`.
 - `open-mistral-nemo`: currently points to `open-mistral-nemo-2407`.
 - `mistral-small-latest`: currently points to `mistral-small-2409`. 
-- `codestral-latest`: currently points to `codestral-2405`.
+- `codestral-latest`: currently points to `codestral-2501`.
 
 ## Model deprecation
 ### Overview
@@ -82,4 +82,5 @@ To prepare for model retirements and version upgrades, we recommend that custome
 | Mistral Medium  | | :heavy_check_mark: | Ideal for intermediate tasks that require moderate reasoning | 32k  | `mistral-medium-2312`| 23.12 |2024/11/25|2024/11/30|2025/03/30|`mistral-small-latest`|
 | Mistral Small 24.02|  | :heavy_check_mark: | Our latest enterprise-grade small model with the first version released Feb. 2024 | 32k  | `mistral-small-2402` | 24.09| 2024/11/25|2024/11/30|2025/03/30| `mistral-small-latest`|
 | Mistral Large 24.02  | | :heavy_check_mark: |Our top-tier reasoning model for high-complexity tasks with the the first version released Feb. 2024. Learn more on our [blog post](https://mistral.ai/news/mistral-large/) | 32k   | `mistral-large-2402`| 24.02|2024/11/25|2024/11/30|2025/03/30| `mistral-large-latest` | 
-| Mistral Large 24.07  | :heavy_check_mark: <br/> [Mistral Research License](https://mistral.ai/licenses/MRL-0.1.md) | :heavy_check_mark: |Our top-tier reasoning model for high-complexity tasks with the the second version released July 2024. Learn more on our [blog post](https://mistral.ai/news/mistral-large-2407/) | 128k   | `mistral-large-2407`| 24.02|2024/11/25|2024/11/30|2025/03/30| `mistral-large-latest`|
+| Mistral Large 24.07  | :heavy_check_mark: <br/> [Mistral Research License](https://mistral.ai/licenses/MRL-0.1.md) | :heavy_check_mark: |Our top-tier reasoning model for high-complexity tasks with the the second version released July 2024. Learn more on our [blog post](https://mistral.ai/news/mistral-large-2407/) | 131k   | `mistral-large-2407`| 24.02|2024/11/25|2024/11/30|2025/03/30| `mistral-large-latest`|
+| Codestral |:heavy_check_mark: <br/> [Mistral Non-Production License](https://mistral.ai/licenses/MNPL-0.1.md) | :heavy_check_mark: | Our cutting-edge language model for coding with the first version released [May 2024](https://mistral.ai/news/codestral/) | 32k  | `codestral-2405` | 24.05| 2024/12/02|2024/12/02|2025/03/30| `codestral-latest`|
diff --git a/docs/guides/tokenization.mdx b/docs/guides/tokenization.mdx
@@ -58,7 +58,7 @@ Tekken proved more proficient in compressing text for approximately 85% of all l
 Our tokenization vocabulary is released in the https://github.com/mistralai/mistral-common/tree/main/tests/data folder. Let’s take a look at the vocabulary of our v3 tekken tokenizer. 
 
 #### Vocabulary size
-Our vocabulary consists of 130k vocab + 1k control tokens. We can use up to 131k tokens and we current use 128k tokens. 
+Our vocabulary consists of 130k vocab + 1k control tokens.  
 
 #### Control tokens 
 Our vocabulary starts with 14 control tokens, which are special tokens we use in the encoding process to represent specific instructions or indicators: