From b83ad27306bcf94c7af580f76d146967761a57bf Mon Sep 17 00:00:00 2001 From: KarthiDreamr Date: Tue, 7 Jul 2026 12:04:44 +0530 Subject: [PATCH 1/4] docs: refresh Google Gemini model examples --- .../pre_configured_ai/google.mdx | 22 ++++++++++--------- 1 file changed, 12 insertions(+), 10 deletions(-) diff --git a/content/docs/configuration/pre_configured_ai/google.mdx b/content/docs/configuration/pre_configured_ai/google.mdx index b878c2504..0c7ec21dd 100644 --- a/content/docs/configuration/pre_configured_ai/google.mdx +++ b/content/docs/configuration/pre_configured_ai/google.mdx @@ -40,23 +40,23 @@ Some reverse proxies do not support the `X-goog-api-key` header. You can configu GOOGLE_AUTH_HEADER=true ``` -Since fetching the models list isn't yet supported, you should set the models you want to use in the .env file. +Since fetching the models list isn't yet supported, you should set the models you want to use in the `.env` file. -For your convenience, these are the latest models as of 5/18/24 that can be used with the Generative Language API: +Google updates Gemini model names frequently, so refer to the **[official Gemini models list](https://ai.google.dev/gemini-api/docs/models)** for the latest identifiers. + +For example, you can start with a small set of currently available Gemini models such as: ```bash filename=".env" -GOOGLE_MODELS=gemini-1.5-flash-latest,gemini-1.0-pro,gemini-1.0-pro-001,gemini-1.0-pro-latest,gemini-1.0-pro-vision-latest,gemini-1.5-pro-latest,gemini-pro,gemini-pro-vision +GOOGLE_MODELS=gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite ``` -- A gemini-pro model or `gemini-pro-vision` are required in your list for attaching images. +- Use a multimodal Gemini model such as `gemini-2.5-flash` or `gemini-2.5-pro` if you want to support image or PDF inputs. - Using LibreChat, PaLM2 and Codey models can only be accessed through Vertex AI, not the Generative Language API. - Only models that support the `generateContent` method can be used natively with LibreChat + the Gen AI API. -- Selecting `gemini-pro-vision` for messages with attachments is not necessary as it will be switched behind the scenes for you. -- Since `gemini-pro-vision` does not accept non-attachment messages, messages without attachments are automatically switched to use `gemini-pro` otherwise Google responds with an error. - With the Google endpoint, you cannot use both Vertex AI and Generative Language API at the same time. You must choose one or the other. -- Some PaLM/Codey models and `gemini-pro-vision` may fail when `maxOutputTokens` is set to a high value. If you encounter this issue, try reducing the value through the conversation parameters. +- Some older PaLM/Codey models may fail when `maxOutputTokens` is set to a high value. If you encounter this issue, try reducing the value through the conversation parameters. @@ -168,12 +168,14 @@ GOOGLE_LOC=us-central1 GOOGLE_CLOUD_LOCATION=global ``` -Since fetching the models list isn't yet supported, you should set the models you want to use in the .env file. +Since fetching the models list isn't yet supported, you should set the models you want to use in the `.env` file. + +Google updates Gemini model names frequently, so refer to the **[official Gemini models list](https://ai.google.dev/gemini-api/docs/models)** for the latest identifiers. -For your convenience, these are the latest models as of 5/18/24 that can be used with the Generative Language API: +For example, you can start with a small set of currently available Gemini models such as: ```bash filename=".env" -GOOGLE_MODELS=gemini-1.5-flash-preview-0514,gemini-1.5-pro-preview-0514,gemini-1.0-pro-vision-001,gemini-1.0-pro-002,gemini-1.0-pro-001,gemini-pro-vision,gemini-1.0-pro +GOOGLE_MODELS=gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite ``` From bfadf812ad63e52978e543e153204193bbe1ebcf Mon Sep 17 00:00:00 2001 From: KarthiDreamr Date: Tue, 7 Jul 2026 12:07:06 +0530 Subject: [PATCH 2/4] docs: add Gemini example check date --- content/docs/configuration/pre_configured_ai/google.mdx | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/content/docs/configuration/pre_configured_ai/google.mdx b/content/docs/configuration/pre_configured_ai/google.mdx index 0c7ec21dd..5a4cedb81 100644 --- a/content/docs/configuration/pre_configured_ai/google.mdx +++ b/content/docs/configuration/pre_configured_ai/google.mdx @@ -44,6 +44,8 @@ Since fetching the models list isn't yet supported, you should set the models yo Google updates Gemini model names frequently, so refer to the **[official Gemini models list](https://ai.google.dev/gemini-api/docs/models)** for the latest identifiers. +The example below was last checked on **2026-07-07**. + For example, you can start with a small set of currently available Gemini models such as: ```bash filename=".env" @@ -172,6 +174,8 @@ Since fetching the models list isn't yet supported, you should set the models yo Google updates Gemini model names frequently, so refer to the **[official Gemini models list](https://ai.google.dev/gemini-api/docs/models)** for the latest identifiers. +The example below was last checked on **2026-07-07**. + For example, you can start with a small set of currently available Gemini models such as: ```bash filename=".env" From 0f3d198092e9305ba9e6fba752e17742058d43cf Mon Sep 17 00:00:00 2001 From: KarthiDreamr Date: Tue, 7 Jul 2026 18:38:11 +0530 Subject: [PATCH 3/4] docs: add current Gemini model ids --- content/docs/configuration/pre_configured_ai/google.mdx | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/content/docs/configuration/pre_configured_ai/google.mdx b/content/docs/configuration/pre_configured_ai/google.mdx index 5a4cedb81..fb2fbacf7 100644 --- a/content/docs/configuration/pre_configured_ai/google.mdx +++ b/content/docs/configuration/pre_configured_ai/google.mdx @@ -49,7 +49,7 @@ The example below was last checked on **2026-07-07**. For example, you can start with a small set of currently available Gemini models such as: ```bash filename=".env" -GOOGLE_MODELS=gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite +GOOGLE_MODELS=gemini-2.5-flash,gemini-2.5-pro,gemini-2.5-flash-lite,gemini-flash-latest,gemini-flash-lite-latest,gemini-pro-latest,gemini-3-pro-preview,gemini-3-flash-preview,gemini-3.1-pro-preview,gemini-3.1-pro-preview-customtools,gemini-3.1-flash-lite,gemini-3.5-flash ``` @@ -179,7 +179,7 @@ The example below was last checked on **2026-07-07**. For example, you can start with a small set of currently available Gemini models such as: ```bash filename=".env" -GOOGLE_MODELS=gemini-2.5-pro,gemini-2.5-flash,gemini-2.5-flash-lite +GOOGLE_MODELS=gemini-2.5-flash,gemini-2.5-pro,gemini-2.5-flash-lite,gemini-flash-latest,gemini-flash-lite-latest,gemini-pro-latest,gemini-3-pro-preview,gemini-3-flash-preview,gemini-3.1-pro-preview,gemini-3.1-pro-preview-customtools,gemini-3.1-flash-lite,gemini-3.5-flash ``` From a2fa792e835c46cddbd624ee38d4ff8b371825f5 Mon Sep 17 00:00:00 2001 From: KarthiDreamr Date: Tue, 7 Jul 2026 18:44:45 +0530 Subject: [PATCH 4/4] docs: clarify Gemini latest model aliases --- content/docs/configuration/pre_configured_ai/google.mdx | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/content/docs/configuration/pre_configured_ai/google.mdx b/content/docs/configuration/pre_configured_ai/google.mdx index fb2fbacf7..2d2a898e0 100644 --- a/content/docs/configuration/pre_configured_ai/google.mdx +++ b/content/docs/configuration/pre_configured_ai/google.mdx @@ -54,11 +54,10 @@ GOOGLE_MODELS=gemini-2.5-flash,gemini-2.5-pro,gemini-2.5-flash-lite,gemini-flash -- Use a multimodal Gemini model such as `gemini-2.5-flash` or `gemini-2.5-pro` if you want to support image or PDF inputs. +- `gemini-flash-latest`, `gemini-flash-lite-latest`, and `gemini-pro-latest` point to the latest available model for each variant, so they are usually safer choices over time as Google deprecates older fixed model IDs. - Using LibreChat, PaLM2 and Codey models can only be accessed through Vertex AI, not the Generative Language API. - Only models that support the `generateContent` method can be used natively with LibreChat + the Gen AI API. - With the Google endpoint, you cannot use both Vertex AI and Generative Language API at the same time. You must choose one or the other. -- Some older PaLM/Codey models may fail when `maxOutputTokens` is set to a high value. If you encounter this issue, try reducing the value through the conversation parameters.