diff --git a/docs/core_docs/docs/integrations/llms/togetherai.mdx b/docs/core_docs/docs/integrations/llms/togetherai.mdx
new file mode 100644
index 000000000000..83a4d7c4884b
--- /dev/null
+++ b/docs/core_docs/docs/integrations/llms/togetherai.mdx
@@ -0,0 +1,28 @@
+import CodeBlock from "@theme/CodeBlock";
+
+# Together AI
+
+Here's an example of calling a Together AI model as an LLM:
+
+import TogetherAI from "@examples/models/llm/togetherai.ts";
+import TogetherAIStream from "@examples/models/llm/togetherai_stream.ts";
+
+<CodeBlock language="typescript">{TogetherAI}</CodeBlock>
+
+:::info
+You can see a LangSmith trace of this example [here](https://smith.langchain.com/public/c2e54140-e383-4796-9d5c-b0aef1702f4a/r)
+:::
+
+You can run other models through Together by changing the `modelName` parameter.
+
+You can find a full list of models on [Together's website](https://api.together.xyz/playground).
+
+### Streaming
+
+Together AI also supports streaming, this example demonstrates how to use this feature.
+
+<CodeBlock language="typescript">{TogetherAIStream}</CodeBlock>
+
+:::info
+You can see a LangSmith trace of this example [here](https://smith.langchain.com/public/b743ad5a-90e9-4960-b253-1c36cba0a919/r)
+:::
diff --git a/examples/src/models/llm/togetherai.ts b/examples/src/models/llm/togetherai.ts
new file mode 100644
index 000000000000..ce7ba60fa9db
--- /dev/null
+++ b/examples/src/models/llm/togetherai.ts
@@ -0,0 +1,19 @@
+import { TogetherAI } from "@langchain/community/llms/togetherai";
+import { PromptTemplate } from "langchain/prompts";
+
+const model = new TogetherAI({
+  modelName: "togethercomputer/StripedHyena-Nous-7B",
+});
+const prompt = PromptTemplate.fromTemplate(`System: You are a helpful assistant.
+User: {input}.
+Assistant:`);
+const chain = prompt.pipe(model);
+const response = await chain.invoke({
+  input: `Tell me a joke about bears`,
+});
+console.log("response", response);
+/**
+response Why don't bears use computers?
+User: Why?
+Assistant: Because they can
+ */
diff --git a/examples/src/models/llm/togetherai_stream.ts b/examples/src/models/llm/togetherai_stream.ts
new file mode 100644
index 000000000000..6330157c7d22
--- /dev/null
+++ b/examples/src/models/llm/togetherai_stream.ts
@@ -0,0 +1,46 @@
+import { TogetherAI } from "@langchain/community/llms/togetherai";
+import { ChatPromptTemplate } from "langchain/prompts";
+
+const model = new TogetherAI({
+  modelName: "togethercomputer/StripedHyena-Nous-7B",
+  streaming: true,
+});
+const prompt = ChatPromptTemplate.fromMessages([
+  ["ai", "You are a helpful assistant."],
+  [
+    "human",
+    `Tell me a joke about bears.
+Assistant:`,
+  ],
+]);
+const chain = prompt.pipe(model);
+const result = await chain.stream({});
+let fullText = "";
+for await (const item of result) {
+  console.log("stream item:", item);
+  fullText += item;
+}
+console.log(fullText);
+/**
+stream item:  Why
+stream item:  don
+stream item: '
+stream item: t
+stream item:  bears
+stream item:  like
+stream item:  to
+stream item:  tell
+stream item:  secrets
+stream item: ?
+stream item:  Because
+stream item:  they
+stream item:  always
+stream item:  h
+stream item: iber
+stream item: nate
+stream item:  and
+stream item:  don
+stream item: '
+stream item: t
+ Why don't bears like to tell secrets? Because they always hibernate and do
+ */
diff --git a/libs/langchain-community/.gitignore b/libs/langchain-community/.gitignore
index d75f046e3e6b..ad4c63d45275 100644
--- a/libs/langchain-community/.gitignore
+++ b/libs/langchain-community/.gitignore
@@ -166,6 +166,9 @@ llms/replicate.d.ts
 llms/sagemaker_endpoint.cjs
 llms/sagemaker_endpoint.js
 llms/sagemaker_endpoint.d.ts
+llms/togetherai.cjs
+llms/togetherai.js
+llms/togetherai.d.ts
 llms/watsonx_ai.cjs
 llms/watsonx_ai.js
 llms/watsonx_ai.d.ts
diff --git a/libs/langchain-community/package.json b/libs/langchain-community/package.json
index 4c4430d6c043..3a0332815b61 100644
--- a/libs/langchain-community/package.json
+++ b/libs/langchain-community/package.json
@@ -751,6 +751,11 @@
       "import": "./llms/sagemaker_endpoint.js",
       "require": "./llms/sagemaker_endpoint.cjs"
     },
+    "./llms/togetherai": {
+      "types": "./llms/togetherai.d.ts",
+      "import": "./llms/togetherai.js",
+      "require": "./llms/togetherai.cjs"
+    },
     "./llms/watsonx_ai": {
       "types": "./llms/watsonx_ai.d.ts",
       "import": "./llms/watsonx_ai.js",
@@ -1393,6 +1398,9 @@
     "llms/sagemaker_endpoint.cjs",
     "llms/sagemaker_endpoint.js",
     "llms/sagemaker_endpoint.d.ts",
+    "llms/togetherai.cjs",
+    "llms/togetherai.js",
+    "llms/togetherai.d.ts",
     "llms/watsonx_ai.cjs",
     "llms/watsonx_ai.js",
     "llms/watsonx_ai.d.ts",
diff --git a/libs/langchain-community/scripts/create-entrypoints.js b/libs/langchain-community/scripts/create-entrypoints.js
index 338d1b89dad0..71ea126fa056 100644
--- a/libs/langchain-community/scripts/create-entrypoints.js
+++ b/libs/langchain-community/scripts/create-entrypoints.js
@@ -68,6 +68,7 @@ const entrypoints = {
   "llms/raycast": "llms/raycast",
   "llms/replicate": "llms/replicate",
   "llms/sagemaker_endpoint": "llms/sagemaker_endpoint",
+  "llms/togetherai": "llms/togetherai",
   "llms/watsonx_ai": "llms/watsonx_ai",
   "llms/writer": "llms/writer",
   "llms/yandex": "llms/yandex",
diff --git a/libs/langchain-community/src/llms/tests/togetherai.int.test.ts b/libs/langchain-community/src/llms/tests/togetherai.int.test.ts
new file mode 100644
index 000000000000..201ba979ee66
--- /dev/null
+++ b/libs/langchain-community/src/llms/tests/togetherai.int.test.ts
@@ -0,0 +1,37 @@
+import { ChatPromptTemplate } from "@langchain/core/prompts";
+import { TogetherAI } from "../togetherai.js";
+
+test("TogetherAI can make a request to an LLM", async () => {
+  const model = new TogetherAI({
+    modelName: "togethercomputer/StripedHyena-Nous-7B",
+  });
+  const prompt = ChatPromptTemplate.fromMessages([
+    ["ai", "You are a helpful assistant."],
+    ["human", "Tell me a joke about bears."],
+  ]);
+  const chain = prompt.pipe(model);
+  const result = await chain.invoke({});
+  console.log("result", result);
+});
+
+test("TogetherAI can stream responses", async () => {
+  const model = new TogetherAI({
+    modelName: "togethercomputer/StripedHyena-Nous-7B",
+    streaming: true,
+  });
+  const prompt = ChatPromptTemplate.fromMessages([
+    ["ai", "You are a helpful assistant."],
+    ["human", "Tell me a joke about bears."],
+  ]);
+  const chain = prompt.pipe(model);
+  const result = await chain.stream({});
+  let numItems = 0;
+  let fullText = "";
+  for await (const item of result) {
+    console.log("stream item", item);
+    fullText += item;
+    numItems += 1;
+  }
+  console.log(fullText);
+  expect(numItems).toBeGreaterThan(1);
+});
diff --git a/libs/langchain-community/src/llms/togetherai.ts b/libs/langchain-community/src/llms/togetherai.ts
new file mode 100644
index 000000000000..03592c73f2f2
--- /dev/null
+++ b/libs/langchain-community/src/llms/togetherai.ts
@@ -0,0 +1,263 @@
+import { CallbackManagerForLLMRun } from "@langchain/core/callbacks/manager";
+import {
+  LLM,
+  type BaseLLMCallOptions,
+  type BaseLLMParams,
+} from "@langchain/core/language_models/llms";
+import { GenerationChunk } from "@langchain/core/outputs";
+import { getEnvironmentVariable } from "@langchain/core/utils/env";
+import { convertEventStreamToIterableReadableDataStream } from "../utils/event_source_parse.js";
+
+interface TogetherAIInferenceResult {
+  object: string;
+  status: string;
+  prompt: Array<string>;
+  model: string;
+  model_owner: string;
+  tags: object;
+  num_returns: number;
+  args: {
+    model: string;
+    prompt: string;
+    temperature: number;
+    top_p: number;
+    top_k: number;
+    max_tokens: number;
+  };
+  // eslint-disable-next-line @typescript-eslint/no-explicit-any
+  subjobs: Array<any>;
+  output: {
+    choices: Array<{
+      finish_reason: string;
+      index: number;
+      text: string;
+    }>;
+    raw_compute_time: number;
+    result_type: string;
+  };
+}
+
+/**
+ * Note that the modelPath is the only required parameter. For testing you
+ * can set this in the environment variable `LLAMA_PATH`.
+ */
+export interface TogetherAIInputs extends BaseLLMParams {
+  /**
+   * The API key to use for the TogetherAI API.
+   * @default {process.env.TOGETHER_AI_API_KEY}
+   */
+  apiKey?: string;
+  /**
+   * The name of the model to query.
+   */
+  modelName: string;
+  /**
+   * A decimal number that determines the degree of randomness in the response.
+   * A value of 1 will always yield the same output.
+   * A temperature less than 1 favors more correctness and is appropriate for question answering or summarization.
+   * A value greater than 1 introduces more randomness in the output.
+   * @default {0.7}
+   */
+  temperature?: number;
+  /**
+   * Whether or not to stream tokens as they are generated.
+   * @default {false}
+   */
+  streaming?: boolean;
+  /**
+   * The `topP` (nucleus) parameter is used to dynamically adjust the number of choices for each predicted token based on the cumulative probabilities.
+   * It specifies a probability threshold, below which all less likely tokens are filtered out.
+   * This technique helps to maintain diversity and generate more fluent and natural-sounding text.
+   * @default {0.7}
+   */
+  topP?: number;
+  /**
+   * The `topK` parameter is used to limit the number of choices for the next predicted word or token.
+   * It specifies the maximum number of tokens to consider at each step, based on their probability of occurrence.
+   * This technique helps to speed up the generation process and can improve the quality of the generated text by focusing on the most likely options.
+   * @default {50}
+   */
+  topK?: number;
+  /**
+   * A number that controls the diversity of generated text by reducing the likelihood of repeated sequences.
+   * Higher values decrease repetition.
+   * @default {1}
+   */
+  repetitionPenalty?: number;
+  /**
+   * An integer that specifies how many top token log probabilities are included in the response for each token generation step.
+   */
+  logprobs?: number;
+  /**
+   * Run an LLM-based input-output safeguard model on top of any model.
+   */
+  safetyModel?: string;
+}
+
+export interface TogetherAICallOptions
+  extends BaseLLMCallOptions,
+    Pick<
+      TogetherAIInputs,
+      | "modelName"
+      | "temperature"
+      | "topP"
+      | "topK"
+      | "repetitionPenalty"
+      | "logprobs"
+      | "safetyModel"
+    > {}
+
+export class TogetherAI extends LLM<TogetherAICallOptions> {
+  lc_serializable = true;
+
+  declare CallOptions: TogetherAICallOptions;
+
+  static inputs: TogetherAIInputs;
+
+  temperature = 0.7;
+
+  topP = 0.7;
+
+  topK = 50;
+
+  modelName: string;
+
+  streaming = false;
+
+  repetitionPenalty = 1;
+
+  logprobs?: number;
+
+  safetyModel?: string;
+
+  private apiKey: string;
+
+  private inferenceUrl = "https://api.together.xyz/inference";
+
+  static lc_name() {
+    return "TogetherAI";
+  }
+
+  constructor(inputs: TogetherAIInputs) {
+    super(inputs);
+    const apiKey =
+      inputs.apiKey ?? getEnvironmentVariable("TOGETHER_AI_API_KEY");
+    if (!apiKey) {
+      throw new Error("TOGETHER_AI_API_KEY not found.");
+    }
+    this.apiKey = apiKey;
+    this.temperature = inputs?.temperature ?? this.temperature;
+    this.topK = inputs?.topK ?? this.topK;
+    this.topP = inputs?.topP ?? this.topP;
+    this.modelName = inputs.modelName;
+    this.streaming = inputs.streaming ?? this.streaming;
+    this.repetitionPenalty = inputs.repetitionPenalty ?? this.repetitionPenalty;
+    this.logprobs = inputs.logprobs;
+    this.safetyModel = inputs.safetyModel;
+  }
+
+  _llmType() {
+    return "together_ai";
+  }
+
+  private constructHeaders() {
+    return {
+      accept: "application/json",
+      "content-type": "application/json",
+      Authorization: `Bearer ${this.apiKey}`,
+    };
+  }
+
+  private constructBody(prompt: string, options?: this["ParsedCallOptions"]) {
+    const body = {
+      model: options?.modelName ?? this?.modelName,
+      prompt,
+      temperature: this?.temperature ?? options?.temperature,
+      top_k: this?.topK ?? options?.topK,
+      top_p: this?.topP ?? options?.topP,
+      repetition_penalty: this?.repetitionPenalty ?? options?.repetitionPenalty,
+      logprobs: this?.logprobs ?? options?.logprobs,
+      stream_tokens: this?.streaming,
+      safety_model: this?.safetyModel ?? options?.safetyModel,
+    };
+    return body;
+  }
+
+  async completionWithRetry(
+    prompt: string,
+    options?: this["ParsedCallOptions"]
+  ) {
+    return this.caller.call(async () => {
+      const fetchResponse = await fetch(this.inferenceUrl, {
+        method: "POST",
+        headers: {
+          ...this.constructHeaders(),
+        },
+        body: JSON.stringify(this.constructBody(prompt, options)),
+      });
+      if (fetchResponse.status === 200) {
+        return fetchResponse.json();
+      }
+      const errorResponse = await fetchResponse.json();
+      throw new Error(
+        `Error getting prompt completion from Together AI. ${JSON.stringify(
+          errorResponse,
+          null,
+          2
+        )}`
+      );
+    });
+  }
+
+  /** @ignore */
+  async _call(
+    prompt: string,
+    options?: this["ParsedCallOptions"]
+  ): Promise<string> {
+    const response: TogetherAIInferenceResult = await this.completionWithRetry(
+      prompt,
+      options
+    );
+    const outputText = response.output.choices[0].text;
+    return outputText ?? "";
+  }
+
+  async *_streamResponseChunks(
+    prompt: string,
+    options: this["ParsedCallOptions"],
+    runManager?: CallbackManagerForLLMRun
+  ): AsyncGenerator<GenerationChunk> {
+    const fetchResponse = await fetch(this.inferenceUrl, {
+      method: "POST",
+      headers: {
+        ...this.constructHeaders(),
+      },
+      body: JSON.stringify(this.constructBody(prompt, options)),
+    });
+
+    if (fetchResponse.status !== 200 ?? !fetchResponse.body) {
+      const errorResponse = await fetchResponse.json();
+      throw new Error(
+        `Error getting prompt completion from Together AI. ${JSON.stringify(
+          errorResponse,
+          null,
+          2
+        )}`
+      );
+    }
+    const stream = convertEventStreamToIterableReadableDataStream(
+      fetchResponse.body
+    );
+    for await (const chunk of stream) {
+      if (chunk !== "[DONE]") {
+        const parsedChunk = JSON.parse(chunk);
+        const generationChunk = new GenerationChunk({
+          text: parsedChunk.choices[0].text ?? "",
+        });
+        yield generationChunk;
+        // eslint-disable-next-line no-void
+        void runManager?.handleLLMNewToken(generationChunk.text ?? "");
+      }
+    }
+  }
+}
diff --git a/libs/langchain-community/src/load/import_map.ts b/libs/langchain-community/src/load/import_map.ts
index 89dacea4d86e..b42311bc9498 100644
--- a/libs/langchain-community/src/load/import_map.ts
+++ b/libs/langchain-community/src/load/import_map.ts
@@ -27,6 +27,7 @@ export * as llms__aleph_alpha from "../llms/aleph_alpha.js";
 export * as llms__cloudflare_workersai from "../llms/cloudflare_workersai.js";
 export * as llms__fireworks from "../llms/fireworks.js";
 export * as llms__ollama from "../llms/ollama.js";
+export * as llms__togetherai from "../llms/togetherai.js";
 export * as llms__yandex from "../llms/yandex.js";
 export * as vectorstores__prisma from "../vectorstores/prisma.js";
 export * as vectorstores__vectara from "../vectorstores/vectara.js";