diff --git a/pages/blog/2023-11-30_litellm.mdx b/pages/blog/2023-11-30_litellm.mdx
index 358f8aa0d..2180ddcac 100644
--- a/pages/blog/2023-11-30_litellm.mdx
+++ b/pages/blog/2023-11-30_litellm.mdx
@@ -268,7 +268,6 @@ custom:
       titleModel: "gpt-3.5-turbo"
       summarize: false
       summaryModel: "gpt-3.5-turbo"
-      forcePrompt: false
       modelDisplayLabel: "Lite LLM"
 ```
 
diff --git a/pages/docs/configuration/azure.mdx b/pages/docs/configuration/azure.mdx
index 651e801b9..cc2e3f611 100644
--- a/pages/docs/configuration/azure.mdx
+++ b/pages/docs/configuration/azure.mdx
@@ -183,7 +183,6 @@ options={[
 ['serverless', 'boolean', 'Specifies if the group is a serverless inference chat completions endpoint from Azure Model Catalog, for which only a model identifier, baseURL, and apiKey are needed. For more info, see serverless inference endpoints.', 'serverless: true'],
 ['addParams', 'object', 'Adds or overrides additional parameters for Azure OpenAI API requests. Useful for specifying API-specific options as key-value pairs.', 'addParams: {temperature: 0.7}'],
 ['dropParams', 'array', 'Allows for the exclusion of certain default parameters from Azure OpenAI API requests. Useful for APIs that do not accept or recognize specific parameters. This should be specified as a list of strings.', 'dropParams: [top_p, stop]'],
-['forcePrompt', 'boolean', 'Dictates whether to send a prompt parameter instead of messages in the request body. This option is useful when needing to format the request in a manner consistent with OpenAI API expectations, particularly for scenarios preferring a single text payload.', 'forcePrompt: true'],
 ]}
 />
 
@@ -215,7 +214,6 @@ endpoints:
         dropParams:
           - "frequency_penalty"
           - "presence_penalty"
-        forcePrompt: false
         models:
         # ... (model-level configurations)
 ```
@@ -583,4 +581,3 @@ endpoints:
 - Compatibility with LibreChat relies on parity with OpenAI API specs, which at the time of writing, are typically **"Pay-as-you-go"** or "Models as a Service" (MaaS) deployments on Azure AI Studio, that are OpenAI-SDK-compatible with either `v1/completions` or `models/chat/completions` endpoint handling.
 - All models that offer serverless deployments ("Serverless APIs") are compatible from the Azure model catalog. You can filter by "Serverless API" under Deployment options and "Chat completion" under inference tasks to see the full list; however, real time endpoint models have not been tested.
 - These serverless inference endpoint/models may or may not support function calling according to OpenAI API specs, which enables their use with Agents.
-- If using legacy "/v1/completions" (without "chat"), you need to set the `forcePrompt` field to `true` in your [group config.](#group-level-configuration)
diff --git a/pages/docs/configuration/librechat_yaml/ai_endpoints/anyscale.mdx b/pages/docs/configuration/librechat_yaml/ai_endpoints/anyscale.mdx
index 09061b2e1..c2505135a 100644
--- a/pages/docs/configuration/librechat_yaml/ai_endpoints/anyscale.mdx
+++ b/pages/docs/configuration/librechat_yaml/ai_endpoints/anyscale.mdx
@@ -24,7 +24,6 @@ description: Example configuration for Anyscale
       titleModel: "meta-llama/Llama-2-7b-chat-hf"
       summarize: false
       summaryModel: "meta-llama/Llama-2-7b-chat-hf"
-      forcePrompt: false
       modelDisplayLabel: "Anyscale"
 ```
 
diff --git a/pages/docs/configuration/librechat_yaml/ai_endpoints/fireworks.mdx b/pages/docs/configuration/librechat_yaml/ai_endpoints/fireworks.mdx
index 5043f9c69..db055747b 100644
--- a/pages/docs/configuration/librechat_yaml/ai_endpoints/fireworks.mdx
+++ b/pages/docs/configuration/librechat_yaml/ai_endpoints/fireworks.mdx
@@ -25,7 +25,6 @@ description: Example configuration for Fireworks
       titleModel: "accounts/fireworks/models/llama-v2-7b-chat"
       summarize: false 
       summaryModel: "accounts/fireworks/models/llama-v2-7b-chat"
-      forcePrompt: false
       modelDisplayLabel: "Fireworks"
       dropParams: ["user"]
 ```
diff --git a/pages/docs/configuration/librechat_yaml/ai_endpoints/litellm.mdx b/pages/docs/configuration/librechat_yaml/ai_endpoints/litellm.mdx
index 9128dd3d0..c389b8828 100644
--- a/pages/docs/configuration/librechat_yaml/ai_endpoints/litellm.mdx
+++ b/pages/docs/configuration/librechat_yaml/ai_endpoints/litellm.mdx
@@ -21,7 +21,6 @@ description: Example configuration for LiteLLM
       titleModel: "gpt-3.5-turbo"
       summarize: false
       summaryModel: "gpt-3.5-turbo"
-      forcePrompt: false
       modelDisplayLabel: "LiteLLM"
 ```
 
diff --git a/pages/docs/configuration/librechat_yaml/ai_endpoints/mlx.mdx b/pages/docs/configuration/librechat_yaml/ai_endpoints/mlx.mdx
index e4abc03b1..352ef3936 100644
--- a/pages/docs/configuration/librechat_yaml/ai_endpoints/mlx.mdx
+++ b/pages/docs/configuration/librechat_yaml/ai_endpoints/mlx.mdx
@@ -27,7 +27,6 @@ description: Example configuration for Apple MLX
       titleModel: "current_model"
       summarize: false
       summaryModel: "current_model"
-      forcePrompt: false
       modelDisplayLabel: "Apple MLX"
       addParams:
             max_tokens: 2000
diff --git a/pages/docs/configuration/librechat_yaml/ai_endpoints/moonshot.mdx b/pages/docs/configuration/librechat_yaml/ai_endpoints/moonshot.mdx
new file mode 100644
index 000000000..ac6a7896c
--- /dev/null
+++ b/pages/docs/configuration/librechat_yaml/ai_endpoints/moonshot.mdx
@@ -0,0 +1,25 @@
+---
+title: Moonshot
+description: Example configuration for Moonshot AI (Kimi)
+---
+
+# [Moonshot](https://www.moonshot.ai/)
+
+> Moonshot API key: [platform.moonshot.cn](https://platform.moonshot.ai)
+
+**Notes:**
+
+- **Known:** icon provided.
+- **Important:** For models with reasoning/thinking capabilities (e.g., `kimi-k2.5`, `kimi-k2-thinking`), the endpoint `name` **must** be set to `"Moonshot"` (case-insensitive) for interleaved reasoning to work correctly with tool calls. Using a different name will result in errors like `thinking is enabled but reasoning_content is missing in assistant tool call message`. See [Moonshot's documentation](https://platform.moonshot.ai/docs/guide/use-kimi-k2-thinking-model#frequently-asked-questions) for more details.
+
+```yaml filename="librechat.yaml"
+    - name: "Moonshot"
+      apiKey: "${MOONSHOT_API_KEY}"
+      baseURL: "https://api.moonshot.ai/v1"
+      models:
+        default: ["kimi-k2.5"]
+        fetch: true
+      titleConvo: true
+      titleModel: "current_model"
+      modelDisplayLabel: "Moonshot"
+```
diff --git a/pages/docs/configuration/librechat_yaml/ai_endpoints/neurochain.mdx b/pages/docs/configuration/librechat_yaml/ai_endpoints/neurochain.mdx
index e470c96a7..f0109b616 100644
--- a/pages/docs/configuration/librechat_yaml/ai_endpoints/neurochain.mdx
+++ b/pages/docs/configuration/librechat_yaml/ai_endpoints/neurochain.mdx
@@ -26,7 +26,6 @@ description: Example configuration for NeurochainAI
       titleModel: "current_model"
       summarize: false
       summaryModel: "current_model"
-      forcePrompt: false
       modelDisplayLabel: "NeurochainAI"
       iconURL: "https://raw.githubusercontent.com/LibreChat-AI/librechat-config-yaml/refs/heads/main/icons/NeurochainAI.png"
 ```
diff --git a/pages/docs/configuration/librechat_yaml/ai_endpoints/ollama.mdx b/pages/docs/configuration/librechat_yaml/ai_endpoints/ollama.mdx
index 0bca15267..1a0cc5e45 100644
--- a/pages/docs/configuration/librechat_yaml/ai_endpoints/ollama.mdx
+++ b/pages/docs/configuration/librechat_yaml/ai_endpoints/ollama.mdx
@@ -36,7 +36,6 @@ description: Example configuration for Ollama
       titleModel: "current_model"
       summarize: false
       summaryModel: "current_model"
-      forcePrompt: false
       modelDisplayLabel: "Ollama"
 ```
 
@@ -60,7 +59,6 @@ However, in case you experience the behavior where `llama3` does not stop genera
       titleModel: "current_model"
       summarize: false
       summaryModel: "current_model"
-      forcePrompt: false
       modelDisplayLabel: "Ollama"
       addParams:
           "stop": [
diff --git a/pages/docs/configuration/librechat_yaml/ai_endpoints/perplexity.mdx b/pages/docs/configuration/librechat_yaml/ai_endpoints/perplexity.mdx
index b7398ae9e..3073c2792 100644
--- a/pages/docs/configuration/librechat_yaml/ai_endpoints/perplexity.mdx
+++ b/pages/docs/configuration/librechat_yaml/ai_endpoints/perplexity.mdx
@@ -32,7 +32,6 @@ description: Example configuration for Perplexity
       titleModel: "llama-3-sonar-small-32k-chat"
       summarize: false
       summaryModel: "llama-3-sonar-small-32k-chat"
-      forcePrompt: false
       dropParams: ["stop", "frequency_penalty"]
       modelDisplayLabel: "Perplexity"
 ```
diff --git a/pages/docs/configuration/librechat_yaml/ai_endpoints/portkey.mdx b/pages/docs/configuration/librechat_yaml/ai_endpoints/portkey.mdx
index cb8fc5922..286a0f990 100644
--- a/pages/docs/configuration/librechat_yaml/ai_endpoints/portkey.mdx
+++ b/pages/docs/configuration/librechat_yaml/ai_endpoints/portkey.mdx
@@ -33,7 +33,6 @@ description: Example configuration for Portkey AI
         titleModel: "current_model"
         summarize: false
         summaryModel: "current_model"
-        forcePrompt: false
         modelDisplayLabel: "Portkey:OpenAI"
         iconURL: https://images.crunchbase.com/image/upload/c_pad,f_auto,q_auto:eco,dpr_1/rjqy7ghvjoiu4cd1xjbf
 ```
@@ -55,7 +54,6 @@ description: Example configuration for Portkey AI
       titleModel: "current_model"
       summarize: false
       summaryModel: "current_model"
-      forcePrompt: false
       modelDisplayLabel: "Portkey:Llama"
       iconURL: https://images.crunchbase.com/image/upload/c_pad,f_auto,q_auto:eco,dpr_1/rjqy7ghvjoiu4cd1xjbf
 ```
diff --git a/pages/docs/configuration/librechat_yaml/ai_endpoints/shuttleai.mdx b/pages/docs/configuration/librechat_yaml/ai_endpoints/shuttleai.mdx
index aee5a6057..e1919e35f 100644
--- a/pages/docs/configuration/librechat_yaml/ai_endpoints/shuttleai.mdx
+++ b/pages/docs/configuration/librechat_yaml/ai_endpoints/shuttleai.mdx
@@ -24,7 +24,6 @@ description: Example configuration for ShuttleAI
       titleModel: "shuttle-2.5-mini"
       summarize: false
       summaryModel: "shuttle-2.5-mini"
-      forcePrompt: false
       modelDisplayLabel: "ShuttleAI"
       dropParams: ["user", "stop"]
 ```
diff --git a/pages/docs/configuration/librechat_yaml/ai_endpoints/togetherai.mdx b/pages/docs/configuration/librechat_yaml/ai_endpoints/togetherai.mdx
index 0584cec94..b1c64d383 100644
--- a/pages/docs/configuration/librechat_yaml/ai_endpoints/togetherai.mdx
+++ b/pages/docs/configuration/librechat_yaml/ai_endpoints/togetherai.mdx
@@ -168,6 +168,5 @@ with open("models_togetherai.json", "w") as file:
       titleModel: "togethercomputer/llama-2-7b-chat"
       summarize: false
       summaryModel: "togethercomputer/llama-2-7b-chat"
-      forcePrompt: false
       modelDisplayLabel: "together.ai"
 ```
\ No newline at end of file
diff --git a/pages/docs/configuration/librechat_yaml/ai_endpoints/truefoundry.mdx b/pages/docs/configuration/librechat_yaml/ai_endpoints/truefoundry.mdx
index 9f53a7e31..d14b74119 100644
--- a/pages/docs/configuration/librechat_yaml/ai_endpoints/truefoundry.mdx
+++ b/pages/docs/configuration/librechat_yaml/ai_endpoints/truefoundry.mdx
@@ -25,7 +25,6 @@ To use [TrueFoundry's AI Gateway](https://www.truefoundry.com/ai-gateway) follow
         titleModel: "current_model"
         summarize: false
         summaryModel: "current_model"
-        forcePrompt: false
         modelDisplayLabel: "TrueFoundry:OpenAI"
 ```
 For more details you can check: [TrueFoundry Docs](https://docs.truefoundry.com/docs/introduction)
\ No newline at end of file
diff --git a/pages/docs/configuration/librechat_yaml/ai_endpoints/vllm.mdx b/pages/docs/configuration/librechat_yaml/ai_endpoints/vllm.mdx
index 5489c0cba..b5c22eb5e 100644
--- a/pages/docs/configuration/librechat_yaml/ai_endpoints/vllm.mdx
+++ b/pages/docs/configuration/librechat_yaml/ai_endpoints/vllm.mdx
@@ -27,7 +27,6 @@ description: Example configuration for vLLM
       titleMessageRole: "user"
       summarize: false
       summaryModel: "current_model"
-      forcePrompt: false
 ```
 
 The configuration above connects LibreChat to a local vLLM server running on port 8023. It uses the Gemma 3 27B model as the default model, but will fetch all available models from your vLLM server.
diff --git a/pages/docs/configuration/librechat_yaml/ai_endpoints/xai.mdx b/pages/docs/configuration/librechat_yaml/ai_endpoints/xai.mdx
index 8299e62a9..623f9367f 100644
--- a/pages/docs/configuration/librechat_yaml/ai_endpoints/xai.mdx
+++ b/pages/docs/configuration/librechat_yaml/ai_endpoints/xai.mdx
@@ -23,7 +23,6 @@ description: Example configuration for xAI
       titleModel: "grok-beta"
       summarize: false
       summaryModel: "grok-beta"
-      forcePrompt: false
       modelDisplayLabel: "Grok"
 ```
 
diff --git a/pages/docs/configuration/librechat_yaml/example.mdx b/pages/docs/configuration/librechat_yaml/example.mdx
index cc8bf7c85..27f457711 100644
--- a/pages/docs/configuration/librechat_yaml/example.mdx
+++ b/pages/docs/configuration/librechat_yaml/example.mdx
@@ -45,7 +45,6 @@ endpoints:
       titleModel: "meta-llama/Llama-2-7b-chat-hf"
       summarize: false
       summaryModel: "meta-llama/Llama-2-7b-chat-hf"
-      forcePrompt: false
       modelDisplayLabel: "Anyscale"
 
     # APIpie
@@ -99,7 +98,6 @@ endpoints:
       titleModel: "accounts/fireworks/models/llama-v2-7b-chat"
       summarize: false
       summaryModel: "accounts/fireworks/models/llama-v2-7b-chat"
-      forcePrompt: false
       modelDisplayLabel: "Fireworks"
       dropParams: ["user"]
   
@@ -148,7 +146,6 @@ endpoints:
       titleModel: "gpt-3.5-turbo"
       summarize: false
       summaryModel: "gpt-3.5-turbo"
-      forcePrompt: false
       modelDisplayLabel: "OpenRouter"
 
     # Perplexity
@@ -168,7 +165,6 @@ endpoints:
       titleModel: "sonar-medium-chat"
       summarize: false
       summaryModel: "sonar-medium-chat"
-      forcePrompt: false
       dropParams: ["stop", "frequency_penalty"]
       modelDisplayLabel: "Perplexity"
 
@@ -185,7 +181,6 @@ endpoints:
       titleModel: "gemini-pro"
       summarize: false
       summaryModel: "llama-summarize"
-      forcePrompt: false
       modelDisplayLabel: "ShuttleAI"
       dropParams: ["user"]
 
@@ -245,7 +240,6 @@ endpoints:
       titleModel: "togethercomputer/llama-2-7b-chat"
       summarize: false
       summaryModel: "togethercomputer/llama-2-7b-chat"
-      forcePrompt: false
       modelDisplayLabel: "together.ai"
 ```
 
@@ -379,9 +373,6 @@ endpoints:
       # Summary Model: Specify the model to use if summarization is enabled.
       # summaryModel: "mistral-tiny"  # Defaults to "gpt-3.5-turbo" if omitted.
 
-      # Force Prompt setting: If true, sends a `prompt` parameter instead of `messages`.
-      # forcePrompt: false
-
       # The label displayed for the AI model in messages.
       modelDisplayLabel: 'Mistral' # Default is "AI" when not set.
 
diff --git a/pages/docs/configuration/librechat_yaml/object_structure/azure_openai.mdx b/pages/docs/configuration/librechat_yaml/object_structure/azure_openai.mdx
index 13d490d5c..7b1a1712a 100644
--- a/pages/docs/configuration/librechat_yaml/object_structure/azure_openai.mdx
+++ b/pages/docs/configuration/librechat_yaml/object_structure/azure_openai.mdx
@@ -228,22 +228,6 @@ addParams:
 dropParams: ["stop", "user", "frequency_penalty", "presence_penalty"]
 ```
 
-### forcePrompt
-
-**Key:**
-<OptionTable
-  options={[
-    ['forcePrompt', 'Boolean', 'If `true`, sends a `prompt` parameter instead of `messages`. This combines all messages into a single text payload, following OpenAI format, and uses the `/completions` endpoint of your baseURL rather than `/chat/completions`.', ''],
-  ]}
-/>
-
-**Default:** Not specified
-
-**Example:**
-```yaml filename="endpoints / azureOpenAI / groups / {group_item} / forcePrompt"
-forcePrompt: false
-```
-
 ### models
 
 **Key:**
diff --git a/pages/docs/configuration/librechat_yaml/object_structure/custom_endpoint.mdx b/pages/docs/configuration/librechat_yaml/object_structure/custom_endpoint.mdx
index 0b220fa61..ae0baa46b 100644
--- a/pages/docs/configuration/librechat_yaml/object_structure/custom_endpoint.mdx
+++ b/pages/docs/configuration/librechat_yaml/object_structure/custom_endpoint.mdx
@@ -110,18 +110,25 @@ iconURL: https://github.com/danny-avila/LibreChat/raw/main/docs/assets/LibreChat
 * If you want to use existing project icons, define the endpoint `name` as one of the main endpoints (case-sensitive):
   - "openAI" | "azureOpenAI" | "google" | "anthropic" | "assistants" | "gptPlugins"
 * There are also "known endpoints" (case-insensitive), which have icons provided. If your endpoint `name` matches the following names, you should omit this field:
-  - "Mistral"
-  - "Deepseek"
-  - "OpenRouter"
-  - "groq"
-  - "APIpie"
   - "Anyscale"
+  - "APIpie"
+  - "Cohere"
+  - "Deepseek"
   - "Fireworks"
+  - "groq"
+  - "Helicone"
+  - "Huggingface"
+  - "Mistral"
+  - "MLX"
+  - "Moonshot"
+  - "ollama"
+  - "OpenRouter"
   - "Perplexity"
+  - "Qwen"
+  - "ShuttleAI"
   - "together.ai"
-  - "ollama"
+  - "Unify"
   - "xai"
-  - "MLX"
 
 ## models
 
@@ -361,22 +368,6 @@ summarize: false
 summaryModel: "mistral-tiny"
 ```
 
-## forcePrompt
-
-**Key:**
-<OptionTable
-  options={[
-    ['forcePrompt', 'Boolean', 'If `true`, sends a `prompt` parameter instead of `messages`.', 'Combines all messages into a single text payload or "prompt", following OpenAI format, which uses the `/completions` endpoint of your baseURL rather than `/chat/completions`.'],
-  ]}
-/>
-
-**Default:** `false`
-
-**Example:**
-```yaml filename="endpoints / custom / forcePrompt"
-forcePrompt: false
-```
-
 ## modelDisplayLabel
 
 **Key:**
diff --git a/pages/docs/quick_start/custom_endpoints.mdx b/pages/docs/quick_start/custom_endpoints.mdx
index 8dae05f65..d2f48a317 100644
--- a/pages/docs/quick_start/custom_endpoints.mdx
+++ b/pages/docs/quick_start/custom_endpoints.mdx
@@ -53,7 +53,6 @@ services:
          titleModel: "current_model"
          summarize: false
          summaryModel: "current_model"
-         forcePrompt: false
          modelDisplayLabel: "OpenRouter"
        - name: "Ollama"
          apiKey: "ollama"