diff --git a/README.md b/README.md
index 4249c42bcf8bfcd171cdd3a5b38abe97ae9bea5d..6e3df0df4ab27100067ddb16c4c1863dd6ef3717 100644
--- a/README.md
+++ b/README.md
@@ -71,6 +71,7 @@ Some cool features of AnythingLLM
 - [LM Studio (all models)](https://lmstudio.ai)
 - [LocalAi (all models)](https://localai.io/)
 - [Together AI (chat models)](https://www.together.ai/)
+- [Mistral](https://mistral.ai/)
 
 **Supported Embedding models:**
 
diff --git a/docker/.env.example b/docker/.env.example
index 5bd909af66b46a90fdda3683cf406f6f5f01e0a7..8d33a809d45c9d606a9b8823c8ea97838513b64a 100644
--- a/docker/.env.example
+++ b/docker/.env.example
@@ -44,6 +44,10 @@ GID='1000'
 # TOGETHER_AI_API_KEY='my-together-ai-key'
 # TOGETHER_AI_MODEL_PREF='mistralai/Mixtral-8x7B-Instruct-v0.1'
 
+# LLM_PROVIDER='mistral'
+# MISTRAL_API_KEY='example-mistral-ai-api-key'
+# MISTRAL_MODEL_PREF='mistral-tiny'
+
 ###########################################
 ######## Embedding API SElECTION ##########
 ###########################################
diff --git a/frontend/src/components/LLMSelection/MistralOptions/index.jsx b/frontend/src/components/LLMSelection/MistralOptions/index.jsx
new file mode 100644
index 0000000000000000000000000000000000000000..d5c666415952fa71d316d28088a114aeb53a9aeb
--- /dev/null
+++ b/frontend/src/components/LLMSelection/MistralOptions/index.jsx
@@ -0,0 +1,103 @@
+import { useState, useEffect } from "react";
+import System from "@/models/system";
+
+export default function MistralOptions({ settings }) {
+  const [inputValue, setInputValue] = useState(settings?.MistralApiKey);
+  const [mistralKey, setMistralKey] = useState(settings?.MistralApiKey);
+
+  return (
+    <div className="flex gap-x-4">
+      <div className="flex flex-col w-60">
+        <label className="text-white text-sm font-semibold block mb-4">
+          Mistral API Key
+        </label>
+        <input
+          type="password"
+          name="MistralApiKey"
+          className="bg-zinc-900 text-white placeholder-white placeholder-opacity-60 text-sm rounded-lg focus:border-white block w-full p-2.5"
+          placeholder="Mistral API Key"
+          defaultValue={settings?.MistralApiKey ? "*".repeat(20) : ""}
+          required={true}
+          autoComplete="off"
+          spellCheck={false}
+          onChange={(e) => setInputValue(e.target.value)}
+          onBlur={() => setMistralKey(inputValue)}
+        />
+      </div>
+      <MistralModelSelection settings={settings} apiKey={mistralKey} />
+    </div>
+  );
+}
+
+function MistralModelSelection({ apiKey, settings }) {
+  const [customModels, setCustomModels] = useState([]);
+  const [loading, setLoading] = useState(true);
+
+  useEffect(() => {
+    async function findCustomModels() {
+      if (!apiKey) {
+        setCustomModels([]);
+        setLoading(false);
+        return;
+      }
+      setLoading(true);
+      const { models } = await System.customModels(
+        "mistral",
+        typeof apiKey === "boolean" ? null : apiKey
+      );
+      setCustomModels(models || []);
+      setLoading(false);
+    }
+    findCustomModels();
+  }, [apiKey]);
+
+  if (loading || customModels.length == 0) {
+    return (
+      <div className="flex flex-col w-60">
+        <label className="text-white text-sm font-semibold block mb-4">
+          Chat Model Selection
+        </label>
+        <select
+          name="MistralModelPref"
+          disabled={true}
+          className="bg-zinc-900 border border-gray-500 text-white text-sm rounded-lg block w-full p-2.5"
+        >
+          <option disabled={true} selected={true}>
+            {!!apiKey
+              ? "-- loading available models --"
+              : "-- waiting for API key --"}
+          </option>
+        </select>
+      </div>
+    );
+  }
+
+  return (
+    <div className="flex flex-col w-60">
+      <label className="text-white text-sm font-semibold block mb-4">
+        Chat Model Selection
+      </label>
+      <select
+        name="MistralModelPref"
+        required={true}
+        className="bg-zinc-900 border border-gray-500 text-white text-sm rounded-lg block w-full p-2.5"
+      >
+        {customModels.length > 0 && (
+          <optgroup label="Available Mistral Models">
+            {customModels.map((model) => {
+              return (
+                <option
+                  key={model.id}
+                  value={model.id}
+                  selected={settings?.MistralModelPref === model.id}
+                >
+                  {model.id}
+                </option>
+              );
+            })}
+          </optgroup>
+        )}
+      </select>
+    </div>
+  );
+}
diff --git a/frontend/src/components/Modals/MangeWorkspace/Settings/index.jsx b/frontend/src/components/Modals/MangeWorkspace/Settings/index.jsx
index a3089d68843552c31cccfe27d3c83f05e2e9fcd8..da0e7b9f02a815659209a356a27b0d5c5e5bbe57 100644
--- a/frontend/src/components/Modals/MangeWorkspace/Settings/index.jsx
+++ b/frontend/src/components/Modals/MangeWorkspace/Settings/index.jsx
@@ -27,11 +27,21 @@ function castToType(key, value) {
   return definitions[key].cast(value);
 }
 
+function recommendedSettings(provider = null) {
+  switch (provider) {
+    case "mistral":
+      return { temp: 0 };
+    default:
+      return { temp: 0.7 };
+  }
+}
+
 export default function WorkspaceSettings({ active, workspace, settings }) {
   const { slug } = useParams();
   const formEl = useRef(null);
   const [saving, setSaving] = useState(false);
   const [hasChanges, setHasChanges] = useState(false);
+  const defaults = recommendedSettings(settings?.LLMProvider);
 
   const handleUpdate = async (e) => {
     setSaving(true);
@@ -143,20 +153,20 @@ export default function WorkspaceSettings({ active, workspace, settings }) {
                       This setting controls how "random" or dynamic your chat
                       responses will be.
                       <br />
-                      The higher the number (2.0 maximum) the more random and
+                      The higher the number (1.0 maximum) the more random and
                       incoherent.
                       <br />
-                      <i>Recommended: 0.7</i>
+                      <i>Recommended: {defaults.temp}</i>
                     </p>
                   </div>
                   <input
                     name="openAiTemp"
                     type="number"
                     min={0.0}
-                    max={2.0}
+                    max={1.0}
                     step={0.1}
                     onWheel={(e) => e.target.blur()}
-                    defaultValue={workspace?.openAiTemp ?? 0.7}
+                    defaultValue={workspace?.openAiTemp ?? defaults.temp}
                     className="bg-zinc-900 text-white text-sm rounded-lg focus:ring-blue-500 focus:border-blue-500 block w-full p-2.5"
                     placeholder="0.7"
                     required={true}
diff --git a/frontend/src/media/llmprovider/mistral.jpeg b/frontend/src/media/llmprovider/mistral.jpeg
new file mode 100644
index 0000000000000000000000000000000000000000..1019f495d4d690dd639aa9f4e5751c403b2eff27
Binary files /dev/null and b/frontend/src/media/llmprovider/mistral.jpeg differ
diff --git a/frontend/src/pages/GeneralSettings/LLMPreference/index.jsx b/frontend/src/pages/GeneralSettings/LLMPreference/index.jsx
index bd6ae511dc7d069f5a1c97e23250339a64f797d5..1efa818d3e900e60dd75cdf2dfebcd03b7067c15 100644
--- a/frontend/src/pages/GeneralSettings/LLMPreference/index.jsx
+++ b/frontend/src/pages/GeneralSettings/LLMPreference/index.jsx
@@ -12,6 +12,7 @@ import OllamaLogo from "@/media/llmprovider/ollama.png";
 import LMStudioLogo from "@/media/llmprovider/lmstudio.png";
 import LocalAiLogo from "@/media/llmprovider/localai.png";
 import TogetherAILogo from "@/media/llmprovider/togetherai.png";
+import MistralLogo from "@/media/llmprovider/mistral.jpeg";
 import PreLoader from "@/components/Preloader";
 import OpenAiOptions from "@/components/LLMSelection/OpenAiOptions";
 import AzureAiOptions from "@/components/LLMSelection/AzureAiOptions";
@@ -21,9 +22,10 @@ import LocalAiOptions from "@/components/LLMSelection/LocalAiOptions";
 import NativeLLMOptions from "@/components/LLMSelection/NativeLLMOptions";
 import GeminiLLMOptions from "@/components/LLMSelection/GeminiLLMOptions";
 import OllamaLLMOptions from "@/components/LLMSelection/OllamaLLMOptions";
+import TogetherAiOptions from "@/components/LLMSelection/TogetherAiOptions";
+import MistralOptions from "@/components/LLMSelection/MistralOptions";
 import LLMItem from "@/components/LLMSelection/LLMItem";
 import { MagnifyingGlass } from "@phosphor-icons/react";
-import TogetherAiOptions from "@/components/LLMSelection/TogetherAiOptions";
 
 export default function GeneralLLMPreference() {
   const [saving, setSaving] = useState(false);
@@ -134,6 +136,13 @@ export default function GeneralLLMPreference() {
       options: <TogetherAiOptions settings={settings} />,
       description: "Run open source models from Together AI.",
     },
+    {
+      name: "Mistral",
+      value: "mistral",
+      logo: MistralLogo,
+      options: <MistralOptions settings={settings} />,
+      description: "Run open source models from Mistral AI.",
+    },
     {
       name: "Native",
       value: "native",
diff --git a/frontend/src/pages/OnboardingFlow/Steps/DataHandling/index.jsx b/frontend/src/pages/OnboardingFlow/Steps/DataHandling/index.jsx
index 281f1e8cdd97e8c5f2f5f6a366e6e7856026ba19..3b0046382a9fedc45ba4635a8833d8d3e575a29c 100644
--- a/frontend/src/pages/OnboardingFlow/Steps/DataHandling/index.jsx
+++ b/frontend/src/pages/OnboardingFlow/Steps/DataHandling/index.jsx
@@ -9,6 +9,7 @@ import OllamaLogo from "@/media/llmprovider/ollama.png";
 import TogetherAILogo from "@/media/llmprovider/togetherai.png";
 import LMStudioLogo from "@/media/llmprovider/lmstudio.png";
 import LocalAiLogo from "@/media/llmprovider/localai.png";
+import MistralLogo from "@/media/llmprovider/mistral.jpeg";
 import ChromaLogo from "@/media/vectordbs/chroma.png";
 import PineconeLogo from "@/media/vectordbs/pinecone.png";
 import LanceDbLogo from "@/media/vectordbs/lancedb.png";
@@ -91,6 +92,13 @@ const LLM_SELECTION_PRIVACY = {
     ],
     logo: TogetherAILogo,
   },
+  mistral: {
+    name: "Mistral",
+    description: [
+      "Your prompts and document text used in response creation are visible to Mistral",
+    ],
+    logo: MistralLogo,
+  },
 };
 
 const VECTOR_DB_PRIVACY = {
diff --git a/frontend/src/pages/OnboardingFlow/Steps/LLMPreference/index.jsx b/frontend/src/pages/OnboardingFlow/Steps/LLMPreference/index.jsx
index dc060594edf41910f94f565016e06e537ef21a6e..9e8ab84a908947e834b9bcf6067b5d42fbe8d1f6 100644
--- a/frontend/src/pages/OnboardingFlow/Steps/LLMPreference/index.jsx
+++ b/frontend/src/pages/OnboardingFlow/Steps/LLMPreference/index.jsx
@@ -9,6 +9,7 @@ import LMStudioLogo from "@/media/llmprovider/lmstudio.png";
 import LocalAiLogo from "@/media/llmprovider/localai.png";
 import TogetherAILogo from "@/media/llmprovider/togetherai.png";
 import AnythingLLMIcon from "@/media/logo/anything-llm-icon.png";
+import MistralLogo from "@/media/llmprovider/mistral.jpeg";
 import OpenAiOptions from "@/components/LLMSelection/OpenAiOptions";
 import AzureAiOptions from "@/components/LLMSelection/AzureAiOptions";
 import AnthropicAiOptions from "@/components/LLMSelection/AnthropicAiOptions";
@@ -17,6 +18,7 @@ import LocalAiOptions from "@/components/LLMSelection/LocalAiOptions";
 import NativeLLMOptions from "@/components/LLMSelection/NativeLLMOptions";
 import GeminiLLMOptions from "@/components/LLMSelection/GeminiLLMOptions";
 import OllamaLLMOptions from "@/components/LLMSelection/OllamaLLMOptions";
+import MistralOptions from "@/components/LLMSelection/MistralOptions";
 import LLMItem from "@/components/LLMSelection/LLMItem";
 import System from "@/models/system";
 import paths from "@/utils/paths";
@@ -109,6 +111,13 @@ export default function LLMPreference({
       options: <TogetherAiOptions settings={settings} />,
       description: "Run open source models from Together AI.",
     },
+    {
+      name: "Mistral",
+      value: "mistral",
+      logo: MistralLogo,
+      options: <MistralOptions settings={settings} />,
+      description: "Run open source models from Mistral AI.",
+    },
     {
       name: "Native",
       value: "native",
diff --git a/server/.env.example b/server/.env.example
index d060e0ab50133b2dea8bfa1814a6be8e8e54606d..26c51927cfeac0a9397b43021f17c013cb129b7c 100644
--- a/server/.env.example
+++ b/server/.env.example
@@ -41,6 +41,10 @@ JWT_SECRET="my-random-string-for-seeding" # Please generate random string at lea
 # TOGETHER_AI_API_KEY='my-together-ai-key'
 # TOGETHER_AI_MODEL_PREF='mistralai/Mixtral-8x7B-Instruct-v0.1'
 
+# LLM_PROVIDER='mistral'
+# MISTRAL_API_KEY='example-mistral-ai-api-key'
+# MISTRAL_MODEL_PREF='mistral-tiny'
+
 ###########################################
 ######## Embedding API SElECTION ##########
 ###########################################
diff --git a/server/models/systemSettings.js b/server/models/systemSettings.js
index cd008d420f02342d8bf5e12e59f504bfb00e0363..53d42f2e2ed61174f7d6cae4552be1711b704d02 100644
--- a/server/models/systemSettings.js
+++ b/server/models/systemSettings.js
@@ -159,6 +159,18 @@ const SystemSettings = {
             AzureOpenAiEmbeddingModelPref: process.env.EMBEDDING_MODEL_PREF,
           }
         : {}),
+      ...(llmProvider === "mistral"
+        ? {
+            MistralApiKey: !!process.env.MISTRAL_API_KEY,
+            MistralModelPref: process.env.MISTRAL_MODEL_PREF,
+
+            // For embedding credentials when mistral is selected.
+            OpenAiKey: !!process.env.OPEN_AI_KEY,
+            AzureOpenAiEndpoint: process.env.AZURE_OPENAI_ENDPOINT,
+            AzureOpenAiKey: !!process.env.AZURE_OPENAI_KEY,
+            AzureOpenAiEmbeddingModelPref: process.env.EMBEDDING_MODEL_PREF,
+          }
+        : {}),
       ...(llmProvider === "native"
         ? {
             NativeLLMModelPref: process.env.NATIVE_LLM_MODEL_PREF,
diff --git a/server/utils/AiProviders/anthropic/index.js b/server/utils/AiProviders/anthropic/index.js
index 17f2abc4acde3ed4b3fcd0d74303df2fbd6df01b..56d3a80f0a4232bbfa107c1f2290a56a7fdacb06 100644
--- a/server/utils/AiProviders/anthropic/index.js
+++ b/server/utils/AiProviders/anthropic/index.js
@@ -26,6 +26,7 @@ class AnthropicLLM {
       );
     this.embedder = embedder;
     this.answerKey = v4().split("-")[0];
+    this.defaultTemp = 0.7;
   }
 
   streamingEnabled() {
diff --git a/server/utils/AiProviders/azureOpenAi/index.js b/server/utils/AiProviders/azureOpenAi/index.js
index f59fc51fa11b73010662dd0d0870d8ade102a908..639ac102ed14e6966f56c76417ac01028b507764 100644
--- a/server/utils/AiProviders/azureOpenAi/index.js
+++ b/server/utils/AiProviders/azureOpenAi/index.js
@@ -25,6 +25,7 @@ class AzureOpenAiLLM {
         "No embedding provider defined for AzureOpenAiLLM - falling back to AzureOpenAiEmbedder for embedding!"
       );
     this.embedder = !embedder ? new AzureOpenAiEmbedder() : embedder;
+    this.defaultTemp = 0.7;
   }
 
   #appendContext(contextTexts = []) {
@@ -93,7 +94,7 @@ class AzureOpenAiLLM {
     );
     const textResponse = await this.openai
       .getChatCompletions(this.model, messages, {
-        temperature: Number(workspace?.openAiTemp ?? 0.7),
+        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
         n: 1,
       })
       .then((res) => {
@@ -130,7 +131,7 @@ class AzureOpenAiLLM {
       this.model,
       messages,
       {
-        temperature: Number(workspace?.openAiTemp ?? 0.7),
+        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
         n: 1,
       }
     );
diff --git a/server/utils/AiProviders/gemini/index.js b/server/utils/AiProviders/gemini/index.js
index 348c8f5ed4c8e2de3cec084f0823100fad4ae823..63549fb8dd86043aae7a6db53ae5e765b9caa867 100644
--- a/server/utils/AiProviders/gemini/index.js
+++ b/server/utils/AiProviders/gemini/index.js
@@ -22,6 +22,7 @@ class GeminiLLM {
         "INVALID GEMINI LLM SETUP. No embedding engine has been set. Go to instance settings and set up an embedding interface to use Gemini as your LLM."
       );
     this.embedder = embedder;
+    this.defaultTemp = 0.7; // not used for Gemini
   }
 
   #appendContext(contextTexts = []) {
diff --git a/server/utils/AiProviders/lmStudio/index.js b/server/utils/AiProviders/lmStudio/index.js
index 614808034c501eb41d24842ba582c3853acb32b4..08950a7b964f42e1f1235ff4444e103998716468 100644
--- a/server/utils/AiProviders/lmStudio/index.js
+++ b/server/utils/AiProviders/lmStudio/index.js
@@ -25,6 +25,7 @@ class LMStudioLLM {
         "INVALID LM STUDIO SETUP. No embedding engine has been set. Go to instance settings and set up an embedding interface to use LMStudio as your LLM."
       );
     this.embedder = embedder;
+    this.defaultTemp = 0.7;
   }
 
   #appendContext(contextTexts = []) {
@@ -85,7 +86,7 @@ class LMStudioLLM {
     const textResponse = await this.lmstudio
       .createChatCompletion({
         model: this.model,
-        temperature: Number(workspace?.openAiTemp ?? 0.7),
+        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
         n: 1,
         messages: await this.compressMessages(
           {
@@ -122,7 +123,7 @@ class LMStudioLLM {
     const streamRequest = await this.lmstudio.createChatCompletion(
       {
         model: this.model,
-        temperature: Number(workspace?.openAiTemp ?? 0.7),
+        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
         n: 1,
         stream: true,
         messages: await this.compressMessages(
diff --git a/server/utils/AiProviders/localAi/index.js b/server/utils/AiProviders/localAi/index.js
index 6623ac88ee357708956a4b35bb5ae2c508eba84e..6d265cf82886ff9a9b41ae0360f0cce6c0cb2f2c 100644
--- a/server/utils/AiProviders/localAi/index.js
+++ b/server/utils/AiProviders/localAi/index.js
@@ -27,6 +27,7 @@ class LocalAiLLM {
         "INVALID LOCAL AI SETUP. No embedding engine has been set. Go to instance settings and set up an embedding interface to use LocalAI as your LLM."
       );
     this.embedder = embedder;
+    this.defaultTemp = 0.7;
   }
 
   #appendContext(contextTexts = []) {
@@ -85,7 +86,7 @@ class LocalAiLLM {
     const textResponse = await this.openai
       .createChatCompletion({
         model: this.model,
-        temperature: Number(workspace?.openAiTemp ?? 0.7),
+        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
         n: 1,
         messages: await this.compressMessages(
           {
@@ -123,7 +124,7 @@ class LocalAiLLM {
       {
         model: this.model,
         stream: true,
-        temperature: Number(workspace?.openAiTemp ?? 0.7),
+        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
         n: 1,
         messages: await this.compressMessages(
           {
diff --git a/server/utils/AiProviders/mistral/index.js b/server/utils/AiProviders/mistral/index.js
new file mode 100644
index 0000000000000000000000000000000000000000..a25185c763126c6a35bb477be78ec895db987183
--- /dev/null
+++ b/server/utils/AiProviders/mistral/index.js
@@ -0,0 +1,184 @@
+const { chatPrompt } = require("../../chats");
+
+class MistralLLM {
+  constructor(embedder = null, modelPreference = null) {
+    const { Configuration, OpenAIApi } = require("openai");
+    if (!process.env.MISTRAL_API_KEY)
+      throw new Error("No Mistral API key was set.");
+
+    const config = new Configuration({
+      basePath: "https://api.mistral.ai/v1",
+      apiKey: process.env.MISTRAL_API_KEY,
+    });
+    this.openai = new OpenAIApi(config);
+    this.model =
+      modelPreference || process.env.MISTRAL_MODEL_PREF || "mistral-tiny";
+    this.limits = {
+      history: this.promptWindowLimit() * 0.15,
+      system: this.promptWindowLimit() * 0.15,
+      user: this.promptWindowLimit() * 0.7,
+    };
+
+    if (!embedder)
+      console.warn(
+        "No embedding provider defined for MistralLLM - falling back to OpenAiEmbedder for embedding!"
+      );
+    this.embedder = embedder;
+    this.defaultTemp = 0.0;
+  }
+
+  #appendContext(contextTexts = []) {
+    if (!contextTexts || !contextTexts.length) return "";
+    return (
+      "\nContext:\n" +
+      contextTexts
+        .map((text, i) => {
+          return `[CONTEXT ${i}]:\n${text}\n[END CONTEXT ${i}]\n\n`;
+        })
+        .join("")
+    );
+  }
+
+  streamingEnabled() {
+    return "streamChat" in this && "streamGetChatCompletion" in this;
+  }
+
+  promptWindowLimit() {
+    return 32000;
+  }
+
+  async isValidChatCompletionModel(modelName = "") {
+    return true;
+  }
+
+  constructPrompt({
+    systemPrompt = "",
+    contextTexts = [],
+    chatHistory = [],
+    userPrompt = "",
+  }) {
+    const prompt = {
+      role: "system",
+      content: `${systemPrompt}${this.#appendContext(contextTexts)}`,
+    };
+    return [prompt, ...chatHistory, { role: "user", content: userPrompt }];
+  }
+
+  async isSafe(_ = "") {
+    return { safe: true, reasons: [] };
+  }
+
+  async sendChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
+    if (!(await this.isValidChatCompletionModel(this.model)))
+      throw new Error(
+        `Mistral chat: ${this.model} is not valid for chat completion!`
+      );
+
+    const textResponse = await this.openai
+      .createChatCompletion({
+        model: this.model,
+        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
+        messages: await this.compressMessages(
+          {
+            systemPrompt: chatPrompt(workspace),
+            userPrompt: prompt,
+            chatHistory,
+          },
+          rawHistory
+        ),
+      })
+      .then((json) => {
+        const res = json.data;
+        if (!res.hasOwnProperty("choices"))
+          throw new Error("Mistral chat: No results!");
+        if (res.choices.length === 0)
+          throw new Error("Mistral chat: No results length!");
+        return res.choices[0].message.content;
+      })
+      .catch((error) => {
+        throw new Error(
+          `Mistral::createChatCompletion failed with: ${error.message}`
+        );
+      });
+
+    return textResponse;
+  }
+
+  async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
+    if (!(await this.isValidChatCompletionModel(this.model)))
+      throw new Error(
+        `Mistral chat: ${this.model} is not valid for chat completion!`
+      );
+
+    const streamRequest = await this.openai.createChatCompletion(
+      {
+        model: this.model,
+        stream: true,
+        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
+        messages: await this.compressMessages(
+          {
+            systemPrompt: chatPrompt(workspace),
+            userPrompt: prompt,
+            chatHistory,
+          },
+          rawHistory
+        ),
+      },
+      { responseType: "stream" }
+    );
+
+    return streamRequest;
+  }
+
+  async getChatCompletion(messages = null, { temperature = 0.7 }) {
+    if (!(await this.isValidChatCompletionModel(this.model)))
+      throw new Error(
+        `Mistral chat: ${this.model} is not valid for chat completion!`
+      );
+
+    const { data } = await this.openai.createChatCompletion({
+      model: this.model,
+      messages,
+      temperature,
+    });
+
+    if (!data.hasOwnProperty("choices")) return null;
+    return data.choices[0].message.content;
+  }
+
+  async streamGetChatCompletion(messages = null, { temperature = 0.7 }) {
+    if (!(await this.isValidChatCompletionModel(this.model)))
+      throw new Error(
+        `Mistral chat: ${this.model} is not valid for chat completion!`
+      );
+
+    const streamRequest = await this.openai.createChatCompletion(
+      {
+        model: this.model,
+        stream: true,
+        messages,
+        temperature,
+      },
+      { responseType: "stream" }
+    );
+    return streamRequest;
+  }
+
+  // Simple wrapper for dynamic embedder & normalize interface for all LLM implementations
+  async embedTextInput(textInput) {
+    return await this.embedder.embedTextInput(textInput);
+  }
+  async embedChunks(textChunks = []) {
+    return await this.embedder.embedChunks(textChunks);
+  }
+
+  async compressMessages(promptArgs = {}, rawHistory = []) {
+    const { messageArrayCompressor } = require("../../helpers/chat");
+    const messageArray = this.constructPrompt(promptArgs);
+    return await messageArrayCompressor(this, messageArray, rawHistory);
+  }
+}
+
+module.exports = {
+  MistralLLM,
+};
diff --git a/server/utils/AiProviders/native/index.js b/server/utils/AiProviders/native/index.js
index 66cc84d0ca3e69bb3cabaff125937ef305185eff..fff904c462548b09ffbb7ca622780b5ae1209ef1 100644
--- a/server/utils/AiProviders/native/index.js
+++ b/server/utils/AiProviders/native/index.js
@@ -29,6 +29,7 @@ class NativeLLM {
 
     // Make directory when it does not exist in existing installations
     if (!fs.existsSync(this.cacheDir)) fs.mkdirSync(this.cacheDir);
+    this.defaultTemp = 0.7;
   }
 
   async #initializeLlamaModel(temperature = 0.7) {
@@ -132,7 +133,7 @@ class NativeLLM {
       );
 
       const model = await this.#llamaClient({
-        temperature: Number(workspace?.openAiTemp ?? 0.7),
+        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
       });
       const response = await model.call(messages);
       return response.content;
@@ -145,7 +146,7 @@ class NativeLLM {
 
   async streamChat(chatHistory = [], prompt, workspace = {}, rawHistory = []) {
     const model = await this.#llamaClient({
-      temperature: Number(workspace?.openAiTemp ?? 0.7),
+      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
     });
     const messages = await this.compressMessages(
       {
diff --git a/server/utils/AiProviders/ollama/index.js b/server/utils/AiProviders/ollama/index.js
index fce96f369844bbd0269a59e05186c3f8b3fee27c..af7fe8210f29bba55518f0e8314a75566b2a6b3f 100644
--- a/server/utils/AiProviders/ollama/index.js
+++ b/server/utils/AiProviders/ollama/index.js
@@ -20,6 +20,7 @@ class OllamaAILLM {
         "INVALID OLLAMA SETUP. No embedding engine has been set. Go to instance settings and set up an embedding interface to use Ollama as your LLM."
       );
     this.embedder = embedder;
+    this.defaultTemp = 0.7;
   }
 
   #ollamaClient({ temperature = 0.07 }) {
@@ -113,7 +114,7 @@ class OllamaAILLM {
     );
 
     const model = this.#ollamaClient({
-      temperature: Number(workspace?.openAiTemp ?? 0.7),
+      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
     });
     const textResponse = await model
       .pipe(new StringOutputParser())
@@ -136,7 +137,7 @@ class OllamaAILLM {
     );
 
     const model = this.#ollamaClient({
-      temperature: Number(workspace?.openAiTemp ?? 0.7),
+      temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
     });
     const stream = await model
       .pipe(new StringOutputParser())
diff --git a/server/utils/AiProviders/openAi/index.js b/server/utils/AiProviders/openAi/index.js
index 038d201d1b395bdfad9188b69c180e030c3eb115..582bc054d2ae8e682644e971f202e94d83aca924 100644
--- a/server/utils/AiProviders/openAi/index.js
+++ b/server/utils/AiProviders/openAi/index.js
@@ -23,6 +23,7 @@ class OpenAiLLM {
         "No embedding provider defined for OpenAiLLM - falling back to OpenAiEmbedder for embedding!"
       );
     this.embedder = !embedder ? new OpenAiEmbedder() : embedder;
+    this.defaultTemp = 0.7;
   }
 
   #appendContext(contextTexts = []) {
@@ -127,7 +128,7 @@ class OpenAiLLM {
     const textResponse = await this.openai
       .createChatCompletion({
         model: this.model,
-        temperature: Number(workspace?.openAiTemp ?? 0.7),
+        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
         n: 1,
         messages: await this.compressMessages(
           {
@@ -165,7 +166,7 @@ class OpenAiLLM {
       {
         model: this.model,
         stream: true,
-        temperature: Number(workspace?.openAiTemp ?? 0.7),
+        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
         n: 1,
         messages: await this.compressMessages(
           {
diff --git a/server/utils/AiProviders/togetherAi/index.js b/server/utils/AiProviders/togetherAi/index.js
index 44061dd0a4f101f29e3973e1352d3401db366a1a..341661f8dba9c5377b6c9720f02e8560d4e35fdb 100644
--- a/server/utils/AiProviders/togetherAi/index.js
+++ b/server/utils/AiProviders/togetherAi/index.js
@@ -28,6 +28,7 @@ class TogetherAiLLM {
         "INVALID TOGETHER AI SETUP. No embedding engine has been set. Go to instance settings and set up an embedding interface to use Together AI as your LLM."
       );
     this.embedder = embedder;
+    this.defaultTemp = 0.7;
   }
 
   #appendContext(contextTexts = []) {
@@ -89,7 +90,7 @@ class TogetherAiLLM {
     const textResponse = await this.openai
       .createChatCompletion({
         model: this.model,
-        temperature: Number(workspace?.openAiTemp ?? 0.7),
+        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
         n: 1,
         messages: await this.compressMessages(
           {
@@ -127,7 +128,7 @@ class TogetherAiLLM {
       {
         model: this.model,
         stream: true,
-        temperature: Number(workspace?.openAiTemp ?? 0.7),
+        temperature: Number(workspace?.openAiTemp ?? this.defaultTemp),
         n: 1,
         messages: await this.compressMessages(
           {
diff --git a/server/utils/chats/index.js b/server/utils/chats/index.js
index d63de47d5ef353609072fe7bcfe84f25b185850f..764c7795a64664f072c99e14179cf6acc844bd84 100644
--- a/server/utils/chats/index.js
+++ b/server/utils/chats/index.js
@@ -171,7 +171,7 @@ async function chatWithWorkspace(
 
   // Send the text completion.
   const textResponse = await LLMConnector.getChatCompletion(messages, {
-    temperature: workspace?.openAiTemp ?? 0.7,
+    temperature: workspace?.openAiTemp ?? LLMConnector.defaultTemp,
   });
 
   if (!textResponse) {
diff --git a/server/utils/chats/stream.js b/server/utils/chats/stream.js
index ceea8d7d2fdbd88c2961f9caf8c7b1ed03bc85d2..cff565ed6e2bf7ad647adc3cb4a3d4d2a7c6ca1c 100644
--- a/server/utils/chats/stream.js
+++ b/server/utils/chats/stream.js
@@ -141,7 +141,7 @@ async function streamChatWithWorkspace(
       `\x1b[31m[STREAMING DISABLED]\x1b[0m Streaming is not available for ${LLMConnector.constructor.name}. Will use regular chat method.`
     );
     completeText = await LLMConnector.getChatCompletion(messages, {
-      temperature: workspace?.openAiTemp ?? 0.7,
+      temperature: workspace?.openAiTemp ?? LLMConnector.defaultTemp,
     });
     writeResponseChunk(response, {
       uuid,
@@ -153,7 +153,7 @@ async function streamChatWithWorkspace(
     });
   } else {
     const stream = await LLMConnector.streamGetChatCompletion(messages, {
-      temperature: workspace?.openAiTemp ?? 0.7,
+      temperature: workspace?.openAiTemp ?? LLMConnector.defaultTemp,
     });
     completeText = await handleStreamResponses(response, stream, {
       uuid,
diff --git a/server/utils/helpers/customModels.js b/server/utils/helpers/customModels.js
index 87fe976ec7df06c7e991669f143efed759bce1e9..53c641e75ec1c4fe2729951ee6e6fd5e6ee6dc0f 100644
--- a/server/utils/helpers/customModels.js
+++ b/server/utils/helpers/customModels.js
@@ -5,6 +5,7 @@ const SUPPORT_CUSTOM_MODELS = [
   "ollama",
   "native-llm",
   "togetherai",
+  "mistral",
 ];
 
 async function getCustomModels(provider = "", apiKey = null, basePath = null) {
@@ -20,6 +21,8 @@ async function getCustomModels(provider = "", apiKey = null, basePath = null) {
       return await ollamaAIModels(basePath);
     case "togetherai":
       return await getTogetherAiModels();
+    case "mistral":
+      return await getMistralModels(apiKey);
     case "native-llm":
       return nativeLLMModels();
     default:
@@ -117,6 +120,26 @@ async function getTogetherAiModels() {
   return { models, error: null };
 }
 
+async function getMistralModels(apiKey = null) {
+  const { Configuration, OpenAIApi } = require("openai");
+  const config = new Configuration({
+    apiKey: apiKey || process.env.MISTRAL_API_KEY,
+    basePath: "https://api.mistral.ai/v1",
+  });
+  const openai = new OpenAIApi(config);
+  const models = await openai
+    .listModels()
+    .then((res) => res.data.data.filter((model) => !model.id.includes("embed")))
+    .catch((e) => {
+      console.error(`Mistral:listModels`, e.message);
+      return [];
+    });
+
+  // Api Key was successful so lets save it for future uses
+  if (models.length > 0 && !!apiKey) process.env.MISTRAL_API_KEY = apiKey;
+  return { models, error: null };
+}
+
 function nativeLLMModels() {
   const fs = require("fs");
   const path = require("path");
diff --git a/server/utils/helpers/index.js b/server/utils/helpers/index.js
index 2b1f3dacf489d2f140f1cd3b996435acb089c266..2eed9057cac2dc90750e821cd5c31af07e2be339 100644
--- a/server/utils/helpers/index.js
+++ b/server/utils/helpers/index.js
@@ -52,6 +52,9 @@ function getLLMProvider(modelPreference = null) {
     case "togetherai":
       const { TogetherAiLLM } = require("../AiProviders/togetherAi");
       return new TogetherAiLLM(embedder, modelPreference);
+    case "mistral":
+      const { MistralLLM } = require("../AiProviders/mistral");
+      return new MistralLLM(embedder, modelPreference);
     case "native":
       const { NativeLLM } = require("../AiProviders/native");
       return new NativeLLM(embedder, modelPreference);
@@ -76,6 +79,7 @@ function getEmbeddingEngineSelection() {
       return new LocalAiEmbedder();
     case "native":
       const { NativeEmbedder } = require("../EmbeddingEngines/native");
+      console.log("\x1b[34m[INFO]\x1b[0m Using Native Embedder");
       return new NativeEmbedder();
     default:
       return null;
diff --git a/server/utils/helpers/updateENV.js b/server/utils/helpers/updateENV.js
index 5c43da519489c1986bb05fedb9a757709019d988..54e684029122fe0989175ba48f1cc1c4afdbbfd8 100644
--- a/server/utils/helpers/updateENV.js
+++ b/server/utils/helpers/updateENV.js
@@ -95,6 +95,15 @@ const KEY_MAPPING = {
     checks: [nonZero],
   },
 
+  MistralApiKey: {
+    envKey: "MISTRAL_API_KEY",
+    checks: [isNotEmpty],
+  },
+  MistralModelPref: {
+    envKey: "MISTRAL_MODEL_PREF",
+    checks: [isNotEmpty],
+  },
+
   // Native LLM Settings
   NativeLLMModelPref: {
     envKey: "NATIVE_LLM_MODEL_PREF",
@@ -268,6 +277,7 @@ function supportedLLM(input = "") {
     "ollama",
     "native",
     "togetherai",
+    "mistral",
   ].includes(input);
   return validSelection ? null : `${input} is not a valid LLM provider.`;
 }