From 29915b22148163b25a27922b9f246cad00ef44ca Mon Sep 17 00:00:00 2001 From: C-L-STARK Date: Tue, 6 Oct 2026 00:08:39 +0800 Subject: [PATCH 1/8] docs: add TopxAI custom endpoint page --- .../librechat_yaml/ai_endpoints/meta.json | 1 + .../librechat_yaml/ai_endpoints/topxai.mdx | 47 +++++++++++++++++++ 2 files changed, 48 insertions(+) create mode 100644 content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.json b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.json index c46fe3dfdd..51c957dd3d 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.json +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.json @@ -26,6 +26,7 @@ "portkey", "shuttleai", "togetherai", + "topxai", "truefoundry", "vllm", "vultrcloudinference", diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx new file mode 100644 index 0000000000..6aefc4b519 --- /dev/null +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx @@ -0,0 +1,47 @@ +--- +title: TopxAI +icon: Plug +description: Configure TopxAI as a custom endpoint in LibreChat. +--- + +TopxAI serves Claude, GPT, Grok, GLM, Kimi, DeepSeek and Jev models through one OpenAI-compatible endpoint with one prepaid key. Every model has a fixed USD price per route, listed at [ai.topxea.com/pricing](https://ai.topxea.com/pricing). + +## Get an API key + +Sign in at [ai.topxea.com](https://ai.topxea.com/) and create a key on the **Keys** page; pick **Auto route** so one key covers every model. Add it to your `.env` file: + +```bash filename=".env" +TOPXAI_API_KEY=sk-your-key-here +``` + +## Configuration + +Add the endpoint under `endpoints.custom` in your `librechat.yaml`: + +```yaml filename="librechat.yaml" + - name: "TopxAI" + apiKey: "${TOPXAI_API_KEY}" + baseURL: "https://ai.topxea.com/v1" + models: + default: ["claude-sonnet-5-5", "gpt-6.1-sol", "grok-4.7"] + fetch: true + titleConvo: true + titleModel: "gpt-6.1-sol" + modelDisplayLabel: "TopxAI" +``` + +To pin a fixed model list instead of fetching the catalog, set `fetch: false` and list the models yourself: + +```yaml filename="librechat.yaml" + models: + default: ["claude-sonnet-5-5", "claude-opus-5-5", "gpt-6-astra", "gpt-6.1-sol", "grok-4.7", "kimi-k3", "deepseek-v4-pro"] + fetch: false +``` + +To let each user supply their own key through the LibreChat UI instead of reading one from `.env`, set `apiKey: "user_provided"`. + +## Notes + +- Model ids are the plain names from the [price list](https://ai.topxea.com/api/pricing) (`claude-sonnet-5-5`, `gpt-6.1-sol`, `grok-4.7` and so on), with no provider prefix. +- A key can be pinned to one route (for example `claude-shared`) or set to Auto route; a model the key's route does not sell answers `403` with "Model is not available on this API key route". See [routes and prices](https://ai.topxea.com/docs/shared-pool-official-line-and-auto-route). +- The [API reference](https://ai.topxea.com/docs/api-reference) lists the endpoints; the Claude models are also served on an Anthropic Messages endpoint, which LibreChat's custom endpoints do not use. From 055498d632c6077cddac62e2ffcb442369881f57 Mon Sep 17 00:00:00 2001 From: C-L-STARK Date: Sun, 25 Oct 2026 15:14:35 +0800 Subject: [PATCH 2/8] docs: refresh TopxAI compatible model examples --- .../configuration/librechat_yaml/ai_endpoints/topxai.mdx | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx index 6aefc4b519..a2d15246f1 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx @@ -4,11 +4,11 @@ icon: Plug description: Configure TopxAI as a custom endpoint in LibreChat. --- -TopxAI serves Claude, GPT, Grok, GLM, Kimi, DeepSeek and Jev models through one OpenAI-compatible endpoint with one prepaid key. Every model has a fixed USD price per route, listed at [ai.topxea.com/pricing](https://ai.topxea.com/pricing). +TopxAI serves compatible Claude, GPT, Grok, GLM, Kimi and DeepSeek chat models through one OpenAI-compatible endpoint with one prepaid key. Every model has a fixed USD price per route, listed at [ai.topxea.com/pricing](https://ai.topxea.com/pricing). ## Get an API key -Sign in at [ai.topxea.com](https://ai.topxea.com/) and create a key on the **Keys** page; pick **Auto route** so one key covers every model. Add it to your `.env` file: +Sign in at [ai.topxea.com](https://ai.topxea.com/) and create a key on the **Keys** page; pick **Auto route** so one key covers the available chat models. Add it to your `.env` file: ```bash filename=".env" TOPXAI_API_KEY=sk-your-key-here @@ -34,7 +34,7 @@ To pin a fixed model list instead of fetching the catalog, set `fetch: false` an ```yaml filename="librechat.yaml" models: - default: ["claude-sonnet-5-5", "claude-opus-5-5", "gpt-6-astra", "gpt-6.1-sol", "grok-4.7", "kimi-k3", "deepseek-v4-pro"] + default: ["claude-sonnet-5-5", "claude-opus-5-5", "gpt-6-astra", "gpt-6.1-sol", "grok-4.7", "kimi-k3.1-pro", "deepseek-flash-Abliterated"] fetch: false ``` @@ -45,3 +45,5 @@ To let each user supply their own key through the LibreChat UI instead of readin - Model ids are the plain names from the [price list](https://ai.topxea.com/api/pricing) (`claude-sonnet-5-5`, `gpt-6.1-sol`, `grok-4.7` and so on), with no provider prefix. - A key can be pinned to one route (for example `claude-shared`) or set to Auto route; a model the key's route does not sell answers `403` with "Model is not available on this API key route". See [routes and prices](https://ai.topxea.com/docs/shared-pool-official-line-and-auto-route). - The [API reference](https://ai.topxea.com/docs/api-reference) lists the endpoints; the Claude models are also served on an Anthropic Messages endpoint, which LibreChat's custom endpoints do not use. + +- Jev uses the separate System One API and is not supported by this custom endpoint configuration. From 5345db5783097fb113352821210c279274099102 Mon Sep 17 00:00:00 2001 From: C-L-STARK Date: Fri, 13 Nov 2026 10:52:29 +0800 Subject: [PATCH 3/8] docs: move the TopxAI endpoint to api.topxai.xyz Co-Authored-By: Claude Opus 5.5 --- .../librechat_yaml/ai_endpoints/topxai.mdx | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx index a2d15246f1..44f03d1e76 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx @@ -4,11 +4,11 @@ icon: Plug description: Configure TopxAI as a custom endpoint in LibreChat. --- -TopxAI serves compatible Claude, GPT, Grok, GLM, Kimi and DeepSeek chat models through one OpenAI-compatible endpoint with one prepaid key. Every model has a fixed USD price per route, listed at [ai.topxea.com/pricing](https://ai.topxea.com/pricing). +TopxAI serves compatible Claude, GPT, Grok, GLM, Kimi and DeepSeek chat models through one OpenAI-compatible endpoint with one prepaid key. Every model has a fixed USD price per route, listed at [api.topxai.xyz/pricing](https://api.topxai.xyz/pricing). ## Get an API key -Sign in at [ai.topxea.com](https://ai.topxea.com/) and create a key on the **Keys** page; pick **Auto route** so one key covers the available chat models. Add it to your `.env` file: +Sign in at [api.topxai.xyz](https://api.topxai.xyz/) and create a key on the **Keys** page; pick **Auto route** so one key covers the available chat models. Add it to your `.env` file: ```bash filename=".env" TOPXAI_API_KEY=sk-your-key-here @@ -21,7 +21,7 @@ Add the endpoint under `endpoints.custom` in your `librechat.yaml`: ```yaml filename="librechat.yaml" - name: "TopxAI" apiKey: "${TOPXAI_API_KEY}" - baseURL: "https://ai.topxea.com/v1" + baseURL: "https://api.topxai.xyz/v1" models: default: ["claude-sonnet-5-5", "gpt-6.1-sol", "grok-4.7"] fetch: true @@ -42,8 +42,8 @@ To let each user supply their own key through the LibreChat UI instead of readin ## Notes -- Model ids are the plain names from the [price list](https://ai.topxea.com/api/pricing) (`claude-sonnet-5-5`, `gpt-6.1-sol`, `grok-4.7` and so on), with no provider prefix. -- A key can be pinned to one route (for example `claude-shared`) or set to Auto route; a model the key's route does not sell answers `403` with "Model is not available on this API key route". See [routes and prices](https://ai.topxea.com/docs/shared-pool-official-line-and-auto-route). -- The [API reference](https://ai.topxea.com/docs/api-reference) lists the endpoints; the Claude models are also served on an Anthropic Messages endpoint, which LibreChat's custom endpoints do not use. +- Model ids are the plain names from the [price list](https://api.topxai.xyz/api/pricing) (`claude-sonnet-5-5`, `gpt-6.1-sol`, `grok-4.7` and so on), with no provider prefix. +- A key can be pinned to one route (for example `claude-shared`) or set to Auto route; a model the key's route does not sell answers `403` with "Model is not available on this API key route". See [routes and prices](https://api.topxai.xyz/docs/shared-pool-official-line-and-auto-route). +- The [API reference](https://api.topxai.xyz/docs/api-reference) lists the endpoints; the Claude models are also served on an Anthropic Messages endpoint, which LibreChat's custom endpoints do not use. - Jev uses the separate System One API and is not supported by this custom endpoint configuration. From a4e6debb45035208c57e9db9fee10863863cd060 Mon Sep 17 00:00:00 2001 From: C-L-STARK Date: Wed, 18 Nov 2026 05:28:06 +0800 Subject: [PATCH 4/8] Update TopxAI Astra and Sol to GPT-6.2 --- .../configuration/librechat_yaml/ai_endpoints/topxai.mdx | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx index 44f03d1e76..6ff81a3a0f 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx @@ -23,10 +23,10 @@ Add the endpoint under `endpoints.custom` in your `librechat.yaml`: apiKey: "${TOPXAI_API_KEY}" baseURL: "https://api.topxai.xyz/v1" models: - default: ["claude-sonnet-5-5", "gpt-6.1-sol", "grok-4.7"] + default: ["claude-sonnet-5-5", "gpt-6.2-sol", "grok-4.7"] fetch: true titleConvo: true - titleModel: "gpt-6.1-sol" + titleModel: "gpt-6.2-sol" modelDisplayLabel: "TopxAI" ``` @@ -34,7 +34,7 @@ To pin a fixed model list instead of fetching the catalog, set `fetch: false` an ```yaml filename="librechat.yaml" models: - default: ["claude-sonnet-5-5", "claude-opus-5-5", "gpt-6-astra", "gpt-6.1-sol", "grok-4.7", "kimi-k3.1-pro", "deepseek-flash-Abliterated"] + default: ["claude-sonnet-5-5", "claude-opus-5-5", "gpt-6.2-astra", "gpt-6.2-sol", "grok-4.7", "kimi-k3.1-pro", "deepseek-flash-Abliterated"] fetch: false ``` @@ -42,7 +42,7 @@ To let each user supply their own key through the LibreChat UI instead of readin ## Notes -- Model ids are the plain names from the [price list](https://api.topxai.xyz/api/pricing) (`claude-sonnet-5-5`, `gpt-6.1-sol`, `grok-4.7` and so on), with no provider prefix. +- Model ids are the plain names from the [price list](https://api.topxai.xyz/api/pricing) (`claude-sonnet-5-5`, `gpt-6.2-sol`, `grok-4.7` and so on), with no provider prefix. - A key can be pinned to one route (for example `claude-shared`) or set to Auto route; a model the key's route does not sell answers `403` with "Model is not available on this API key route". See [routes and prices](https://api.topxai.xyz/docs/shared-pool-official-line-and-auto-route). - The [API reference](https://api.topxai.xyz/docs/api-reference) lists the endpoints; the Claude models are also served on an Anthropic Messages endpoint, which LibreChat's custom endpoints do not use. From 9ededbb3d054d0d560b75d6cff0fd232b41b9ad3 Mon Sep 17 00:00:00 2001 From: C-L-STARK Date: Wed, 18 Nov 2026 06:11:56 +0800 Subject: [PATCH 5/8] Use a text-only picker for the TopxAI custom endpoint --- .../librechat_yaml/ai_endpoints/topxai.mdx | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx index 6ff81a3a0f..3dee803693 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx @@ -19,24 +19,20 @@ TOPXAI_API_KEY=sk-your-key-here Add the endpoint under `endpoints.custom` in your `librechat.yaml`: ```yaml filename="librechat.yaml" +endpoints: + custom: - name: "TopxAI" apiKey: "${TOPXAI_API_KEY}" baseURL: "https://api.topxai.xyz/v1" models: - default: ["claude-sonnet-5-5", "gpt-6.2-sol", "grok-4.7"] - fetch: true + default: ["claude-sonnet-5-5", "gpt-6.2-astra", "gpt-6.2-sol", "grok-4.7", "kimi-k3.1-pro", "deepseek-flash-Abliterated"] + fetch: false titleConvo: true titleModel: "gpt-6.2-sol" modelDisplayLabel: "TopxAI" ``` -To pin a fixed model list instead of fetching the catalog, set `fetch: false` and list the models yourself: - -```yaml filename="librechat.yaml" - models: - default: ["claude-sonnet-5-5", "claude-opus-5-5", "gpt-6.2-astra", "gpt-6.2-sol", "grok-4.7", "kimi-k3.1-pro", "deepseek-flash-Abliterated"] - fetch: false -``` +Choose text models available to your key and set `titleModel` to one of them. Keeping `fetch: false` limits the picker to that list. A key with access to several TopxAI routes can also see image, video and System One models in `/v1/models`, which LibreChat's OpenAI-compatible chat configuration cannot use for text conversations. To let each user supply their own key through the LibreChat UI instead of reading one from `.env`, set `apiKey: "user_provided"`. @@ -44,6 +40,4 @@ To let each user supply their own key through the LibreChat UI instead of readin - Model ids are the plain names from the [price list](https://api.topxai.xyz/api/pricing) (`claude-sonnet-5-5`, `gpt-6.2-sol`, `grok-4.7` and so on), with no provider prefix. - A key can be pinned to one route (for example `claude-shared`) or set to Auto route; a model the key's route does not sell answers `403` with "Model is not available on this API key route". See [routes and prices](https://api.topxai.xyz/docs/shared-pool-official-line-and-auto-route). -- The [API reference](https://api.topxai.xyz/docs/api-reference) lists the endpoints; the Claude models are also served on an Anthropic Messages endpoint, which LibreChat's custom endpoints do not use. - -- Jev uses the separate System One API and is not supported by this custom endpoint configuration. +- This example uses Chat Completions. To use Claude through the native Messages API, configure a separate [Anthropic custom endpoint](/docs/configuration/librechat_yaml/object_structure/custom_endpoint#provider) with `provider: anthropic`, `baseURL: "https://api.topxai.xyz"` and an explicit list of Claude model IDs. See the [TopxAI API reference](https://api.topxai.xyz/docs/api-reference). From 371ae2eea8a8c49c8fd24c7a293f4520a6e2ccdb Mon Sep 17 00:00:00 2001 From: TopxAI Date: Wed, 18 Nov 2026 07:51:11 +0800 Subject: [PATCH 6/8] docs: link the TopxAI guide from the custom endpoints index List the guide with the other compatible endpoints so the index and sidebar link the same provider page. --- content/docs/configuration/librechat_yaml/ai_endpoints/index.mdx | 1 + 1 file changed, 1 insertion(+) diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/index.mdx b/content/docs/configuration/librechat_yaml/ai_endpoints/index.mdx index 87e51cbf33..9cf4c08737 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/index.mdx +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/index.mdx @@ -66,6 +66,7 @@ OPENAI_API_KEY=user_provided + From b1bc7fdcaf16ecde99299ad95504e34eb1896db8 Mon Sep 17 00:00:00 2001 From: C-L-STARK Date: Wed, 18 Nov 2026 04:36:37 -0800 Subject: [PATCH 7/8] docs: link TopxAI's current routes page and list the guide in translated sidebars TopxAI moved its routes page to /docs/routes-and-the-auto-route on 2026-11-18 (the old address redirects). Point the TopxAI guide there, and run `pnpm sync:locale-meta` so the translated ai_endpoints sidebars list the page like the English one. --- .../docs/configuration/librechat_yaml/ai_endpoints/meta.de.json | 1 + .../docs/configuration/librechat_yaml/ai_endpoints/meta.es.json | 1 + .../docs/configuration/librechat_yaml/ai_endpoints/meta.fr.json | 1 + .../docs/configuration/librechat_yaml/ai_endpoints/meta.id.json | 1 + .../docs/configuration/librechat_yaml/ai_endpoints/meta.it.json | 1 + .../docs/configuration/librechat_yaml/ai_endpoints/meta.ja.json | 1 + .../docs/configuration/librechat_yaml/ai_endpoints/meta.ko.json | 1 + .../docs/configuration/librechat_yaml/ai_endpoints/meta.nl.json | 1 + .../docs/configuration/librechat_yaml/ai_endpoints/meta.pl.json | 1 + .../configuration/librechat_yaml/ai_endpoints/meta.pt-BR.json | 1 + .../docs/configuration/librechat_yaml/ai_endpoints/meta.tr.json | 1 + .../docs/configuration/librechat_yaml/ai_endpoints/meta.vi.json | 1 + .../docs/configuration/librechat_yaml/ai_endpoints/meta.zh.json | 1 + .../docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx | 2 +- 14 files changed, 14 insertions(+), 1 deletion(-) diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.de.json b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.de.json index 332e7c704c..aabbf2e7ac 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.de.json +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.de.json @@ -26,6 +26,7 @@ "portkey", "shuttleai", "togetherai", + "topxai", "truefoundry", "vllm", "vultrcloudinference", diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.es.json b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.es.json index 3e2bbff757..b70b9a0899 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.es.json +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.es.json @@ -26,6 +26,7 @@ "portkey", "shuttleai", "togetherai", + "topxai", "truefoundry", "vllm", "vultrcloudinference", diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.fr.json b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.fr.json index 757c760a50..bcb7f2e6d1 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.fr.json +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.fr.json @@ -26,6 +26,7 @@ "portkey", "shuttleai", "togetherai", + "topxai", "truefoundry", "vllm", "vultrcloudinference", diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.id.json b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.id.json index 5edda54f1e..d7ba81c750 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.id.json +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.id.json @@ -26,6 +26,7 @@ "portkey", "shuttleai", "togetherai", + "topxai", "truefoundry", "vllm", "vultrcloudinference", diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.it.json b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.it.json index 5edda54f1e..d7ba81c750 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.it.json +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.it.json @@ -26,6 +26,7 @@ "portkey", "shuttleai", "togetherai", + "topxai", "truefoundry", "vllm", "vultrcloudinference", diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.ja.json b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.ja.json index 0811cb6374..9f89b4a493 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.ja.json +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.ja.json @@ -26,6 +26,7 @@ "portkey", "shuttleai", "togetherai", + "topxai", "truefoundry", "vllm", "vultrcloudinference", diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.ko.json b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.ko.json index a514bbd3b1..6ae6133fa8 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.ko.json +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.ko.json @@ -26,6 +26,7 @@ "portkey", "shuttleai", "togetherai", + "topxai", "truefoundry", "vllm", "vultrcloudinference", diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.nl.json b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.nl.json index d6e2495c9c..1e609f5640 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.nl.json +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.nl.json @@ -26,6 +26,7 @@ "portkey", "shuttleai", "togetherai", + "topxai", "truefoundry", "vllm", "vultrcloudinference", diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.pl.json b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.pl.json index d3181723e6..8ac01f93d5 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.pl.json +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.pl.json @@ -26,6 +26,7 @@ "portkey", "shuttleai", "togetherai", + "topxai", "truefoundry", "vllm", "vultrcloudinference", diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.pt-BR.json b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.pt-BR.json index 3e2bbff757..b70b9a0899 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.pt-BR.json +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.pt-BR.json @@ -26,6 +26,7 @@ "portkey", "shuttleai", "togetherai", + "topxai", "truefoundry", "vllm", "vultrcloudinference", diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.tr.json b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.tr.json index 2d2557db3a..01cbeab5a9 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.tr.json +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.tr.json @@ -26,6 +26,7 @@ "portkey", "shuttleai", "togetherai", + "topxai", "truefoundry", "vllm", "vultrcloudinference", diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.vi.json b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.vi.json index 46539e0db6..309b75d6fd 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.vi.json +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.vi.json @@ -26,6 +26,7 @@ "portkey", "shuttleai", "togetherai", + "topxai", "truefoundry", "vllm", "vultrcloudinference", diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.zh.json b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.zh.json index 477cd77592..d17c65c1b5 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.zh.json +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.zh.json @@ -26,6 +26,7 @@ "portkey", "shuttleai", "togetherai", + "topxai", "truefoundry", "vllm", "vultrcloudinference", diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx index 3dee803693..d6fce3f1ae 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx @@ -39,5 +39,5 @@ To let each user supply their own key through the LibreChat UI instead of readin ## Notes - Model ids are the plain names from the [price list](https://api.topxai.xyz/api/pricing) (`claude-sonnet-5-5`, `gpt-6.2-sol`, `grok-4.7` and so on), with no provider prefix. -- A key can be pinned to one route (for example `claude-shared`) or set to Auto route; a model the key's route does not sell answers `403` with "Model is not available on this API key route". See [routes and prices](https://api.topxai.xyz/docs/shared-pool-official-line-and-auto-route). +- A key can be pinned to one route (for example the Claude route, `claude-shared`) or set to Auto route; a model the key's route does not sell answers `403` with "Model is not available on this API key route". See [routes and prices](https://api.topxai.xyz/docs/routes-and-the-auto-route). - This example uses Chat Completions. To use Claude through the native Messages API, configure a separate [Anthropic custom endpoint](/docs/configuration/librechat_yaml/object_structure/custom_endpoint#provider) with `provider: anthropic`, `baseURL: "https://api.topxai.xyz"` and an explicit list of Claude model IDs. See the [TopxAI API reference](https://api.topxai.xyz/docs/api-reference). From 1481168cd590b802804192d0301eda6f578a9294 Mon Sep 17 00:00:00 2001 From: C-L-STARK Date: Thu, 19 Nov 2026 01:54:26 -0800 Subject: [PATCH 8/8] docs: TopxAI's Kimi model is now kimi-k3.1-pro-Abliterated TopxAI replaced kimi-k3.1-pro with kimi-k3.1-pro-Abliterated on 2026-11-19; the old ID now returns 403 (https://api.topxai.xyz/pricing/kimi-k3.1-pro-abliterated). --- .../docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx index d6fce3f1ae..6598ab74e4 100644 --- a/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx +++ b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx @@ -25,7 +25,7 @@ endpoints: apiKey: "${TOPXAI_API_KEY}" baseURL: "https://api.topxai.xyz/v1" models: - default: ["claude-sonnet-5-5", "gpt-6.2-astra", "gpt-6.2-sol", "grok-4.7", "kimi-k3.1-pro", "deepseek-flash-Abliterated"] + default: ["claude-sonnet-5-5", "gpt-6.2-astra", "gpt-6.2-sol", "grok-4.7", "kimi-k3.1-pro-Abliterated", "deepseek-flash-Abliterated"] fetch: false titleConvo: true titleModel: "gpt-6.2-sol"