Model Providers
When deploying LobeHub, a rich set of environment variables related to model service providers is provided, allowing you to easily define the model service providers to be enabled in LobeHub.
OpenAI
ENABLED_OPENAI
- Type:Optional
- Description:Enables OpenAI as a model provider by default, turns off the OpenAI service when set to
0 - Default:
1 - Example:
0
OPENAI_API_KEY
- Type: Required
- Description: This is the API key you applied for on the OpenAI account page, you can check it out here
- Default: -
- Example:
sk-xxxxxx...xxxxxx
OPENAI_PROXY_URL
- Type: Optional
- Description: If you manually configure the OpenAI interface proxy, you can use this configuration item to override the default OpenAI API request base URL
- Default:
https://api.openai.com/v1 - Example:
https://api.chatanywhere.cnorhttps://aihubmix.com/v1
Please check the request suffix of your proxy service provider. Some proxy service providers may
add /v1 to the request suffix, while others may not. If you find that the AI returns an empty
message during testing, try adding the /v1 suffix and retry.
Whether to fill in /v1 is closely related to the model service provider. For example, the
default address of openai is api.openai.com/v1. If your proxy forwards the /v1 interface, you
can simply fill in proxy.com. However, if the model service provider directly forwards the
api.openai.com domain, then you need to add /v1 to the URL yourself.
Related discussions:
- Why is the return value blank after installing Docker, configuring environment variables?
- Reasons for errors when using third-party interfaces
- No response in chat after filling in the proxy server address
OPENAI_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=display_nameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
+qwen-7b-chat,+glm-6b,-gpt-3.5-turbo,gpt-4-turbo=gpt-4o
The above example adds qwen-7b-chat and glm-6b to the model list, removes gpt-3.5-turbo from the list, and displays the name of gpt-4-turbo as gpt-4o. If you want to disable all models first and then enable specific models, you can use -all,+gpt-3.5-turbo, which means only gpt-3.5-turbo will be enabled.
You can find all current model names in modelProviders.
Meta
Use the official Meta Model API. See Using Meta in LobeHub for setup instructions.
META_API_KEY
- Type: Optional for the deployment; required when providing a shared server key. Users can instead enter their own key in Meta provider settings.
- Description: A key created in the Model API dashboard. Setting a non-empty key automatically enables Meta in the server configuration.
ENABLED_METAis derived from this key, not a separate environment switch. LobeHub usesMETA_API_KEY, rather than theMODEL_API_KEYname in Meta's SDK examples. - Default: Unset; no shared server key.
- Example:
your-meta-model-api-key
META_PROXY_URL
- Type: Optional
- Description: Overrides the Meta API base URL. The proxy must support the Responses API. Supply the base URL, not the full
/responsesendpoint. - Default:
https://api.meta.ai/v1 - Example:
https://meta-proxy.example.com/v1
META_MODEL_LIST
- Type: Optional
- Description: Customizes the model list using the shared model-list syntax:
+adds a model,-hides a model, andmodel_id=display_namerenames a model. Separate entries with commas. This does not grant access to models unavailable to your Meta account. - Default: Unset; uses the built-in model list.
- Example:
-all,+muse-spark-1.3
The example hides all default models and adds muse-spark-1.3. See the Muse Spark product page and Meta's Muse Spark 1.3 announcement for version information. Model availability depends on your account's API access.
Azure OpenAI
If you need to use Azure OpenAI to provide model services, you can refer to the Deploying with Azure OpenAI section for detailed steps. Here, we will list the environment variables related to Azure OpenAI.
AZURE_API_KEY
- Type: Required
- Description: This is the API key you applied for on the Azure OpenAI account page
- Default: -
- Example:
c55168be3874490ef0565d9779ecd5a6
AZURE_ENDPOINT
- Type: Required
- Description: The endpoint of Azure OpenAI, you can find it in the Azure OpenAI account page
- Default:
- - Example:
https://docs-test-001.openai.azure.com
AZURE_API_VERSION
- Type: Required
- Description: The API version of Azure, following the format YYYY-MM-DD
- Default:
- - Example:
2023-02-01, refer to latest version
AZURE_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, useid->deploymentName=displayNameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
gpt-35-turbo->my-deploy=GPT 3.5 Turbo或gpt-4-turbo->my-gpt4=GPT 4 Turbo<128000:vision:fc>
Google AI
GOOGLE_API_KEY
- Type: Required
- Description: This is the API key you applied for in the Google AI Platform to access Google AI services
- Default: -
- Example:
AIraDyDwcw254kwJaGjI9wwaHcdDCS__Vt3xQE
GOOGLE_PROXY_URL
- Type: Optional
- Description: If you manually configure the Google API proxy, you can use this configuration item to override the default Google API request base URL
- Default:
https://generativelanguage.googleapis.com - Example:
https://api.genai.gd.edu.kg/google
GOOGLE_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=display_nameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
-all,+gemini-2.5-flash,+gemini-2.5-pro
Vertex AI
VERTEXAI_CREDENTIALS
- Type: Required
- Description: A JSON string of your Google Cloud service account key, you can get the key from here.
- Default: -
- Example:
{"type": "service_account", "project_id": "your-gcp-project-id", ...}
VERTEXAI_PROJECT
- Type: Optional
- Description: Your Google Cloud project ID. If not set, it will be obtained from the
project_idfield inVERTEXAI_CREDENTIALS. - Default: -
- Example:
your-gcp-project-id
VERTEXAI_LOCATION
- Type: Optional
- Description: The region where your Vertex AI model is located.
- Default:
global - Example:
us-central1
VERTEXAI_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=display_nameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
-all,+gemini-2.5-flash,+gemini-2.5-pro
Anthropic AI
ANTHROPIC_API_KEY
- Type: Required
- Description: This is the API key you applied from Anthropic AI
- Default: -
- Example:
sk-ant-apixx-xxxxxxxxx-xxxxxxxxxxxxxxxxx-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx-xxxxxxxx
ANTHROPIC_PROXY_URL
- Type: Optional
- Description: If you manually configure the Anthropic API proxy, you can use this configuration item to override the default Anthropic API request base URL
- Default:
https://api.anthropic.com - Example:
https://my-anthropic-proxy.com
ANTHROPIC_CLIENT_TIMEOUT
- Type: Optional
- Description: Anthropic SDK client request timeout in milliseconds. This timeout is also used by Anthropic-compatible providers that rely on the Anthropic SDK.
- Default:
295000 - Example:
780000
AWS Bedrock
ENABLED_AWS_BEDROCK
- Type:Optional
- Description:Enables AWS Bedrock as a model provider by default, turns on the AWS Bedrock service when set to
1 - Default:
0 - Example:
1
AWS_ACCESS_KEY_ID
- Type: Required
- Description: Access key ID for AWS service authentication
- Default: -
- Example:
AKIA5STVRLFSB4S9HWBR
AWS_SECRET_ACCESS_KEY
- Type: Required
- Description: Key for AWS service authentication
- Default: -
- Example:
Th3vXxLYpuKcv2BARktPSTPxx+jbSiFT6/0w7oEC
AWS_REGION
- Type: Optional
- Description: Region setting for AWS services
- Default:
us-east-1 - Example:
us-east-1
DeepSeek AI
DEEPSEEK_PROXY_URL
- Type: Optional
- Description: If you manually configure the DeepSeek API proxy, you can use this configuration item to override the default DeepSeek API request base URL
- Default:
https://api.deepseek.com/v1 - Example:
https://my-deepseek-proxy.com
DEEPSEEK_API_KEY
- Type: Required
- Description: This is the API key you applied for in the DeepSeek AI service
- Default: -
- Example:
sk-xxxxxx...xxxxxx
DEEPSEEK_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=displayNameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
-all,+deepseek-reasoner
XAI
XAI_API_KEY
- Type: Required
- Description: This is the API key you applied for in the XAI service
- Default: -
- Example:
xai-xxxxxx...xxxxxx
Wenxin
WENXIN_API_KEY
- Type: Required
- Description: This is the API key you applied for in the Baidu Wenxin service
- Default: -
- Example:
xxxxxx...xxxxxx
OpenRouter AI
OPENROUTER_API_KEY
- Type: Required
- Description: This is the API key you applied for in the OpenRouter AI service
- Default: -
- Example:
sk-or-v1-xxxxxx...xxxxxx=
OPENROUTER_MODEL_LIST
- Type: Optional
- Description: Used to specify a custom OpenRouter model list. Model definition syntax rules see model-list
- Default:
- - Example:
-all,+01-ai/yi-34b-chat,+huggingfaceh4/zephyr-7b-beta
PPIO
PPIO_API_KEY
- Type: Required
- Description: This your PPIO API Key.
- Default: -
- Example:
sk_xxxxxxxxxx
PPIO_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=display_nameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
-all,+deepseek/deepseek-v3/community,+deepseek/deepseek-r1-distill-llama-70b
Github
GITHUB_TOKEN
- Type: Required
- Description: This is your Personal access tokens you got for in the Github
- Default:
- - Example:
ghp_xxxxxx...xxxxxx=
GITHUB_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=display_nameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
-all,+gpt-4o,+gpt-4o-mini
TogetherAI
TOGETHERAI_API_KEY
- Type: Required
- Description: This is the API key you applied for in the TogetherAI service
- Default: -
- Example:
xxxxxx...xxxxxx
TOGETHERAI_MODEL_LIST
- Type: Optional
- Description: Used to specify a custom TogetherAI model list. Model definition syntax rules see model-list
- Default:
- - Example:
-all,+meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo,+meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
Fireworks AI
FIREWORKSAI_API_KEY
- Type: Required
- Description: This is the API key you applied for in the Fireworks AI service
- Default:
- - Example:
xxxxxx...xxxxxx
FIREWORKSAI_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=display_nameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
-all,+accounts/fireworks/models/llama-v3p3-70b-instruct,+accounts/fireworks/models/deepseek-v3
Ollama
ENABLED_OLLAMA
- Type:Optional
- Description:Enables Ollama as a model provider by default, turns off the Ollama service when set to
0 - Default:
1 - Example:
0
OLLAMA_PROXY_URL
- Type: Required
- Description: Used to enable the Ollama service, setting this will display optional open-source language models in the language model list and can also specify custom language models
- Default: -
- Example:
http://127.0.0.1:11434
OLLAMA_MODEL_LIST
- Type: Optional
- Description: Used to specify a custom Ollama language model. Model definition syntax rules see model-list
- Default: -
- Example:
llama2:7B
Moonshot AI
MOONSHOT_API_KEY
- Type: Required
- Description: This is the API key you applied for in the Moonshot AI service
- Default: -
- Example:
Y2xpdGhpMzNhZXNoYjVtdnZjMWc6bXNrLWIxQlk3aDNPaXpBWnc0V1RaMDhSRmRFVlpZUWY=
MOONSHOT_PROXY_URL
- Type: Optional
- Description: If you manually configure the Moonshot API proxy, you can use this configuration item to override the default Moonshot API request base URL
- Default:
https://api.moonshot.cn/v1 - Example:
https://my-moonshot-proxy.com/v1
Perplexity AI
PERPLEXITY_API_KEY
- Type: Required
- Description: This is the API key you applied from Perplexity AI
- Default: -
- Example:
pplx-xxxxxx...xxxxxx
PERPLEXITY_PROXY_URL
- Type: Optional
- Description: If you manually configure the Perplexity API proxy, you can use this configuration item to override the default Perplexity API request base URL
- Default:
https://api.Perplexity.ai - Example:
https://my-Perplexity-proxy.com
PERPLEXITY_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=display_nameto customize the display name of a model, separated by commas. Definition syntax rules see - Default:
- - Example:
-all,+sonar-pro,+sonar
Minimax AI
MINIMAX_API_KEY
- Type: Required
- Description: This is the API key you applied for in the Minimax AI service
- Default: -
- Example:
xxxxxx...xxxxxx
Mistral AI
MISTRAL_API_KEY
- Type: Required
- Description: This is the API key you applied for in the Mistral AI service
- Default: -
- Example:
xxxxxx...xxxxxx=
Groq AI
GROQ_API_KEY
- Type: Required
- Description: This is the API key you applied from Groq AI
- Default: -
- Example:
gsk_xxxxxx...xxxxxx
GROQ_PROXY_URL
- Type: Optional
- Description: If you manually configure the Groq API proxy, you can use this configuration item to override the default Groq API request base URL
- Default:
https://api.groq.com/openai/v1 - Example:
https://my-groq-proxy.com/v1
GROQ_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=display_nameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
-all,+llama-3.3-70b-versatile,+llama-3.1-8b-instant
ZHIPU AI
ZHIPU_API_KEY
- Type: Required
- Description: This is the API key you applied for in the ZHIPU AI service
- Default: -
- Example:
4582d332441a313f5c2ed9824d1798ca.rC8EcTAhgbOuAuVT
ZHIPU_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=display_nameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
-all,+glm-4.6,+glm-4-plus
01.AI
ZEROONE_API_KEY
- Type: Required
- Description: This is the API key you applied for in the 01.AI service
- Default: -
- Example:
xxxxxx...xxxxxx
ZEROONE_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=display_nameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
-all,+yi-large,+yi-large-rag
Qiniu
QINIU_API_KEY
- Type: Required
- Description: This is the API key you can obtain from Qiniu AI service
- Default: -
- Example:
sk-xxxxx...xxxxx
QINIU_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=display_nameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
-all,+deepseek-r1,+deepseek-v3
QINIU_PROXY_URL
- Type: Optional
- Description: If you manually configure the Qiniu API proxy, you can use this configuration item to override the default Qiniu API request base URL
- Default:
https://openai.qiniu.com/v1 - Example:
https://my-qiniu-proxy.com/v1
Qwen
QWEN_API_KEY
- Type: Required
- Description: This is the DashScope API key you can obtain from Alibaba Cloud
- Default: -
- Example:
sk-xxxxx...xxxxx
QWEN_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name->deploymentName=display_nameto customize the display name of a model, separated by commas. The deploymentName->deploymentNamecan be omitted, and it defaults to the latest model version. Definition syntax rules see model-list - Default:
- - Example:
-all,+qwen-turbo,+qwen-plus,+qwen-max->qwen-max-2025-01-25
QWEN_PROXY_URL
- Type: Optional
- Description: If you manually configure the Qwen API proxy, you can use this configuration item to override the default Qwen API request base URL
- Default:
https://dashscope.aliyuncs.com/compatible-mode/v1 - Example:
https://my-qwen-proxy.com/v1
Stepfun AI
STEPFUN_API_KEY
- Type: Required
- Description: This is the DashScope API key you can obtain from Stepfun AI service
- Default: -
- Example:
sk-xxxxx...xxxxx
Novita AI
NOVITA_API_KEY
- Type: Required
- Description: This is the API key you applied for in the Novita AI service
- Default: -
- Example:
xxxxxx...xxxxxx
NOVITA_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=display_nameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
-all,+meta-llama/llama-3.1-8b-instruct,+meta-llama/llama-3.3-70b-instruct
BAICHUAN
BAICHUAN_API_KEY
- Type: Required
- Description: This is the API key you applied for in the BAICHUAN service
- Default: -
- Example:
xxxxxx...xxxxxx
TAICHU
TAICHU_API_KEY
- Type: Required
- Description: This is the API key you applied for in the TAICHU service
- Default: -
- Example:
xxxxxx...xxxxxx
360 AI
AI360_API_KEY
- Type: Required
- Description: This is the API key you applied for in the 360 AI service
- Default: -
- Example:
xxxxxx...xxxxxx
Siliconflow
SILICONCLOUD_API_KEY
- Type: Required
- Description: This is the API key you applied from Siliconflow service
- Default: -
- Example:
xxxxxx...xxxxxx
SILICONCLOUD_PROXY_URL
- Type: Optional
- Description: If you manually configure the Siliconflow API proxy, you can use this configuration item to override the default Siliconflow API request base URL
- Default:
https://api.siliconflow.cn/v1 - Example:
https://my-siliconflow-proxy.com/v1
SILICONCLOUD_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=display_nameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
-all,+deepseek-ai/DeepSeek-V2.5,+Qwen/Qwen2.5-7B-Instruct
Upstage AI
UPSTAGE_API_KEY
- Type: Required
- Description: This is the API key you applied from Upstage AI service
- Default: -
- Example:
xxxxxx...xxxxxx
Spark AI
SPARK_API_KEY
- Type: Required
- Description: This is the API key you applied from Spark AI service
- Default: -
- Example:
xxxxxx...xxxxxx
A21 AI
AI21_API_KEY
- Type: Required
- Description: This is the API key you applied from
AI21_API_KEYservice - Default: -
- Example:
xxxxxx...xxxxxx
HUNYUAN
HUNYUAN_API_KEY
- Type: Required
- Description: This is the API key you applied from HUNYUAN service
- Default: -
- Example:
xxxxxx...xxxxxx
HUNYUAN_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=display_nameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
-all,+hunyuan-2.0-instruct-20251111,+hunyuan-2.0-thinking-20251109
Volcengine
VOLCENGINE_API_KEY
- Type: Required
- Description: This is the API key you applied from Volcengine service, you can check it out here
- Default: -
- Example:
ad925b3d-aaaa-bbbb-cccc-51fde2f50547
VOLCENGINE_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name->deploymentName=display_nameto customize the display name of a model, separated by commas. The deploymentName->deploymentNamecan be omitted, and it defaults to the latest model version. Definition syntax rules see model-list - Default:
- - Example:
-all,+deepseek-r1,+deepseek-v3->deepseek-v3-250324,+doubao-1.5-pro-256k,+doubao-1.5-pro-32k->doubao-1-5-pro-32k-250115,+doubao-1.5-lite-32k
VOLCENGINE_PROXY_URL
- Type: Optional
- Description: If you manually configure the Volcengine API proxy, you can use this configuration item to override the default Volcengine API request base URL
- Default:
https://ark.cn-beijing.volces.com/api/v3 - Example:
https://my-volcengine-proxy.com/v1
InfiniAI
INFINIAI_API_KEY
- Type: Required
- Description: This is the API key you applied from Infini-AI, you can check it out here
- Default: -
- Example:
sk-xxxxxx...xxxxxx
INFINIAI_MODEL_LIST
- Type: Optional
- Description: Used to control the model list, use
+to add a model, use-to hide a model, usemodel_name=display_nameto customize the display name of a model, separated by commas. Definition syntax rules see model-list - Default:
- - Example:
-all,+qwq-32b,+deepseek-r1
FAL
ENABLED_FAL
- Type: Optional
- Description: Enables FAL as a model provider by default. Set to
0to disable the FAL service. - Default:
1 - Example:
0
FAL_API_KEY
- Type: Required
- Description: This is the API key you applied for in the FAL service (create one at fal.ai/dashboard/keys). If
FAL_API_KEYis not set, LobeHub readsFAL_KEY, the name fal's own SDKs use. The key powers fal image, video and music generation. Music (MiniMax Music and ACE-Step 1.5) is only available through fal: MiniMax has stopped selling its official music API to new accounts. See Music Generation. - Default: -
- Example:
fal-xxxxxx...xxxxxx
FAL_MODEL_LIST
- Type: Optional
- Description: Used to control the FAL model list. Use
+to add a model,-to hide a model, andmodel_name=display_nameto customize the display name of a model. Separate multiple entries with commas. The definition syntax follows the same rules as other providers' model lists. - Default:
- - Example:
-all,+fal-ai/flux/schnell,+fal-ai/flux-pro/kontext=FLUX.1 Kontext [pro]
The above example disables all models first, then enables fal-ai/flux/schnell and fal-ai/flux-pro/kontext (displayed as FLUX.1 Kontext [pro]).
ElevenLabs
Text-to-speech only. See Using ElevenLabs in LobeHub for setup instructions.
ELEVENLABS_API_KEY
- Type: Optional for the deployment; required when providing a shared server key. Users can instead enter their own key in ElevenLabs provider settings, which takes precedence.
- Description: A key created on the ElevenLabs API Keys page. Setting a non-empty key automatically enables ElevenLabs in the server configuration.
ENABLED_ELEVENLABSis derived from this key, not a separate environment switch. Without a key from either source, speech requests to ElevenLabs fail with anInvalidProviderAPIKeyerror. - Default: Unset; no shared server key.
- Example:
sk_xxxxxx...xxxxxx
ELEVENLABS_PROXY_URL
- Type: Optional
- Description: Overrides the ElevenLabs API base URL, for example a data-residency endpoint. Only used together with the server key. A trailing
/v1is accepted. - Default:
https://api.elevenlabs.io - Example:
https://api.eu.residency.elevenlabs.io
ELEVENLABS_MODEL_LIST
- Type: Optional
- Description: Customizes the ElevenLabs model list using the shared model-list syntax:
+adds a model,-hides a model, andmodel_id=display_namerenames a model. Separate entries with commas. - Default: Unset; uses the built-in model list.
- Example:
-all,+eleven_v4,+eleven_flash_v2_5
The example hides all default models and enables only eleven_v4 and eleven_flash_v2_5.
Fish Audio
Text-to-speech only. See Using Fish Audio in LobeHub for setup instructions.
FISHAUDIO_API_KEY
- Type: Optional for the deployment; required when providing a shared server key. Users can instead enter their own key in Fish Audio provider settings, which takes precedence.
- Description: A key created on the Fish Audio API Keys page. Setting a non-empty key automatically enables Fish Audio in the server configuration.
ENABLED_FISHAUDIOis derived from this key, not a separate environment switch. Without a key from either source, speech requests to Fish Audio fail with anInvalidProviderAPIKeyerror. - Default: Unset; no shared server key.
- Example:
xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
FISHAUDIO_PROXY_URL
- Type: Optional
- Description: Overrides the Fish Audio API base URL. Only used together with the server key. A trailing
/v1is accepted. - Default:
https://api.fish.audio - Example:
https://fish-proxy.example.com
FISHAUDIO_MODEL_LIST
- Type: Optional
- Description: Customizes the Fish Audio model list using the shared model-list syntax.
- Default: Unset; uses the built-in model list.
- Example:
-all,+s2.1-pro
Doubao Speech
Volcengine speech synthesis, text-to-speech only; separate from the Volcengine Ark provider. See Using Doubao Speech in LobeHub for setup instructions. Configure either DOUBAOSPEECH_API_KEY, or DOUBAOSPEECH_APP_ID together with DOUBAOSPEECH_ACCESS_TOKEN. Credentials a user saves in Doubao Speech provider settings take precedence and are never combined with the server's.
DOUBAOSPEECH_API_KEY
- Type: Optional
- Description: An API key from the new Volcengine speech console (API Key management), sent as
X-Api-Key. Used instead of the App ID + Access Token when both are set.ENABLED_DOUBAOSPEECHis derived from the configured credentials, not a separate environment switch. - Default: Unset
- Example:
xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
DOUBAOSPEECH_APP_ID
- Type: Optional
- Description: Legacy speech console App ID, used together with
DOUBAOSPEECH_ACCESS_TOKEN. - Default: Unset
- Example:
1234567890
DOUBAOSPEECH_ACCESS_TOKEN
- Type: Optional
- Description: Legacy speech console Access Token, used together with
DOUBAOSPEECH_APP_ID. - Default: Unset
- Example:
xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
DOUBAOSPEECH_PROXY_URL
- Type: Optional
- Description: Overrides the Doubao Speech API base URL. Only used together with the server credentials. A trailing
/api/v3is accepted. - Default:
https://openspeech.bytedance.com - Example:
https://doubao-proxy.example.com
DOUBAOSPEECH_MODEL_LIST
- Type: Optional
- Description: Customizes the Doubao Speech model list using the shared model-list syntax.
- Default: Unset; uses the built-in model list.
- Example:
-all,+seed-tts-2.0
ComfyUI
ENABLED_COMFYUI
- Type: Optional
- Description: Enables ComfyUI as a model provider by default. Set to
0to disable the ComfyUI service. - Default:
1 - Example:
0
COMFYUI_BASE_URL
- Type: Optional
- Description: The base URL address of the ComfyUI service
- Default:
http://localhost:8188 - Example:
http://192.168.1.100:8188orhttps://my-comfyui-server.com
COMFYUI_AUTH_TYPE
- Type: Optional
- Description: The authentication type for ComfyUI, supporting 4 authentication methods
none: No authentication (default)basic: Basic authentication (username + password)bearer: Bearer Token authentication (API key)custom: Custom request header authentication
- Default:
none - Example:
basic
COMFYUI_API_KEY
- Type: Optional
- Description: The API key used when the authentication type is
bearer - Default: -
- Example:
sk-xxxxxx...xxxxxx
COMFYUI_USERNAME
- Type: Optional
- Description: The username used when the authentication type is
basic - Default: -
- Example:
admin
COMFYUI_PASSWORD
- Type: Optional
- Description: The password used when the authentication type is
basic - Default: -
- Example:
password123
COMFYUI_CUSTOM_HEADERS
- Type: Optional
- Description: Custom request headers used when the authentication type is
custom, requires JSON format string - Default: -
- Example:
{"X-Auth-Token": "your-token", "X-Custom-Header": "value"}
ComfyUI supports multiple authentication methods. Please choose the appropriate authentication type and corresponding authentication parameters according to your ComfyUI service configuration. If your ComfyUI service has no authentication set up, you can skip configuring authentication-related environment variables.
BFL
BFL_API_KEY
- Type: Required
- Description: This is the API key you applied for in the BFL service.
- Default: -
- Example:
12345678-1234-1234-1234-123456789abc
BFL_MODEL_LIST
- Type: Optional
- Description: Used to control the BFL model list. Use
+to add a model,-to hide a model, andmodel_name=display_nameto customize the display name of a model. Separate multiple entries with commas. The definition syntax follows the same rules as other providers' model lists. - Default:
- - Example:
-all,+flux-pro-1.1,+flux-kontext-pro=FLUX.1 Kontext [pro]
The above example disables all models first, then enables flux-pro-1.1 and flux-kontext-pro (displayed as FLUX.1 Kontext [pro]).
NewAPI
NEWAPI_API_KEY
- Type: Optional
- Description: This is the API key for your NewAPI service instance. NewAPI is a multi-provider model aggregation service that provides unified access to various AI model APIs.
- Default: -
- Example:
sk-xxxxxx...xxxxxx
NEWAPI_PROXY_URL
- Type: Optional
- Description: The base URL for your NewAPI server instance. This should point to your deployed NewAPI service endpoint.
- Default: -
- Example:
https://your-newapi-server.com/
NewAPI is a multi-provider model aggregation service that supports automatic model routing based on provider detection. It offers cost management features and provides a single endpoint for accessing models from multiple providers including OpenAI, Anthropic, Google, and more. Learn more about NewAPI at https://github.com/Calcium-Ion/new-api.
Vercel AI Gateway
VERCELAIGATEWAY_API_KEY
- Type: Required
- Description: This is the API key you applied for in the Vercel AI Gateway service.
- Default: -
- Example:
vck_xxxxxx...xxxxxx
VERCELAIGATEWAY_MODEL_LIST
- Type: Optional
- Description: Used to control the Vercel AI Gateway model list. Use
+to add a model,-to hide a model, andmodel_name=display_nameto customize the display name of a model. Separate multiple entries with commas. The definition syntax follows the same rules as other providers' model lists. - Default:
- - Example:
-all,+vercel-model-1,+vercel-model-2=vercel-special
Cerebras
CEREBRAS_API_KEY
- Type: Required
- Description: This is the API key you applied for in the Cerebras service.
- Default: -
- Example:
csk-xxxxxx...xxxxxx
CEREBRAS_MODEL_LIST
- Type: Optional
- Description: Used to control the Cerebras model list. Use
+to add a model,-to hide a model, andmodel_name=display_nameto customize the display name of a model. Separate multiple entries with commas. The definition syntax follows the same rules as other providers' model lists. - Default:
- - Example:
-all,+cerebras-model-1,+cerebras-model-2=cerebras-special
AIHubMix
AIHUBMIX_API_KEY
- Type: Required
- Description: This is the API key you applied for in the AIHubMix service.
- Default: -
- Example:
sk-xxxxxx...xxxxxx
AIHUBMIX_PROXY_URL
- Type: Optional
- Description: The base URL of the AIHubMix gateway. Point this at a mirror or backup endpoint; defaults to the official gateway when unset.
- Default:
https://aihubmix.com - Example:
https://your-aihubmix-endpoint.com
AIHUBMIX_MODEL_LIST
- Type: Optional
- Description: Used to control the AIHubMix model list. Use
+to add a model,-to hide a model, andmodel_name=display_nameto customize the display name of a model. Separate multiple entries with commas. The definition syntax follows the same rules as other providers' model lists. - Default:
- - Example:
-all,+claude-opus-4-1-20250805,+claude-opus-4-20250514=claude-opus-4
Straico
STRAICO_API_KEY
- Type: Required
- Description: This is the API key you applied for in the Straico service.
- Default: -
- Example:
sk-xxxxxx...xxxxxx
STRAICO_MODEL_LIST
- Type: Optional
- Description: Used to control the Straico model list. Use
+to add a model,-to hide a model, andmodel_name=display_nameto customize the display name of a model. Separate multiple entries with commas. The definition syntax follows the same rules as other providers' model lists. - Default:
- - Example:
-all,+straico-model-1,+straico-model-2=straico-special
Unsloth
Connect to your own Unsloth Studio instance. See Using Unsloth in LobeHub for browser authentication and desktop CORS limitations.
UNSLOTH_API_KEY
- Type: Optional for the deployment; set a real Studio key when providing authenticated server access. Users can instead configure their key in provider settings.
- Description: The API key for your Studio instance. A non-empty value enables the provider in server configuration.
ENABLED_UNSLOTHis derived from this key and is not an independent environment switch. Keyless local server access depends on Studio's access policy; cross-origin browser requests require valid authentication. - Default: Unset; no shared server key.
- Example:
your-unsloth-studio-api-key
UNSLOTH_PROXY_URL
- Type: Optional
- Description: Overrides the OpenAI-compatible API base URL. Use an address reachable from the LobeHub server. Inside Docker,
127.0.0.1refers to the container, not the host running Studio. An explicitly configured Studio port overrides its default8888. - Default:
http://127.0.0.1:8888/v1 - Example:
http://studio.example.com:8888/v1
UNSLOTH_MODEL_LIST
- Type: Optional
- Description: Customizes the model list using the shared model-list syntax:
+adds a model,-hides a model, andmodel_id=display_namerenames a model. Separate entries with commas. Use IDs returned by your Studio instance; this setting does not download models. - Default: Unset; uses the built-in example model list with the examples disabled. This does not guarantee local availability or change existing saved model selections.
- Example:
-all,+your-local-model-id=Local Model
magpie
MAGPIE_PROXY_URL
- Type: Optional
- Description: The magpie gateway address the server sends requests to, and with it the switch that stops the browser from sending them. Leave it unset when magpie runs on the user's own machine: the browser reaches
127.0.0.1:3425, which a hosted deployment's server cannot. Set it when magpie runs where the server can reach it: a container, another host, or behind a proxy. A browser cannot reach those directly, because magpie refuses a preflight that carries no gateway key and the browser never sends one. - Default: Unset; the browser sends the requests.
- Example:
http://magpie.example.com:3425/v1