Skip to main content
To add your own models, we have prepared the following guides for you. If you have any questions, contact the Langdock team.

Adding models

Open model dialogue

  1. Go to the model settings and click on Add Model to add a new model to the platform
  2. A modal opens where you can add models. Here, you find two sections:
    • Display Settings at the top allows you to customize what the user sees in the model selector.
    • Model Configuration lets you connect your Langdock workspace to your model API.

Display Settings

To configure the Display settings, you can follow the following steps. This information is also available by the company hosting the model. Provider: The organization that built and trained the model. This doesn’t necessarily align with the company you consume the model from. For example, you can use Microsoft Azure to use OpenAI models in the EU, but the provider will still be OpenAI. Model name: The name of the model. Hosting provider: Where you consume the model. For example, GPT-5 can be hosted by Microsoft Azure. Region: Shows the user where the model is hosted. This can be set to the EU, the US, or Global. Knowledge cutoff: When the model training data ended. Image analysis: Indicates whether the model can analyze images. This information is available from the model provider and the model hoster. Please only enable this setting if the model supports vision/image analysis. Model description: An optional description (max 150 characters) shown to users. You can provide descriptions in English and German using the language toggle.

Model Configurations

To set up the Model Configuration, select the SDK you are using. You will find information on the configuration of the model provider (e.g., Azure or AWS): SDK: The kit or library Langdock needs to use the model you added. Base URL: To send prompts to the corresponding endpoint of your model. Model ID: The name of the model in your configuration (this might not be the “official” model name). API key: Allows your users to authenticate using the model from within Langdock when they send prompts. Context Size: The number of tokens the model can process in its context window. Please use the exact value of the model to ensure the context management in Langdock works correctly. API Type: Choose between Completion API and Responses API depending on the model. Newer models (GPT-5 series, o3, o4 Mini) typically use the Responses API, while older models use the Completion API.

Other configuration options

Maximum messages in 3 hours: Allows you to influence usage/costs and limit messages per user. This setting is optional. Input and output token pricing: Allows you to set the token pricing of the individual model to monitor usage and costs. Reasoning Effort: Determines how much computation the model spends on reasoning. Higher values improve quality but incur extra latency and tokens. Accepted values: None, Minimal, Low, Medium, High. Only available for models using the Responses API. Verbosity: Controls the level of detail in the model’s final answer. Accepted values: Low, Medium, High. Only available for models using the Responses API. Canvas: Whether the model can generate canvas content for collaborative writing and editing. Supports Tools: Whether the model supports tool calling (integrations, web search, etc.). Enabled by default. Tool Calls in Stream: Whether the model can call tools during streaming. Enabled by default. Supports Temperature: Whether the model supports the temperature parameter for controlling randomness. Disable this for reasoning models (o1, o3, o4 Mini, GPT-5, GPT-5 mini, GPT-5 nano) as they reject temperature values. Claude models also don’t support temperature when Display Thinking is enabled. Display Thinking: Shows the model’s reasoning process in the UI. Enable this for reasoning/thinking model variants. Available in Agents: Whether this model can be selected for use in agents. Enabled by default. Visible to everyone: You can set the model to be visible to everyone in the workspace. If this option is disabled, the model is only visible to admins and cannot be used by other users. This allows you to test the model before launching it to the entire workspace. Maintenance mode: Can be activated to show users in the interface that the model might not work as expected. This is useful if you are changing some configuration or there is a temporary issue with the model from your model provider. Strict Mode: Enables strict validation mode for the model’s API calls. User Identifier: Controls whether user identity information is sent to the model provider. Options: None, User ID, Email, or Microsoft UPN (User Principal Name). Image Editing: For image generation models only — indicates whether the model can edit existing images in addition to generating new ones.

Final steps

  1. After entering all mandatory settings, click Save
  2. We recommend testing the model before making it visible to everyone. Send a message to the model and see if there is a response generated by the model. If you run into any issues, contact support@langdock.com

Model-specific configuration

Below are the recommended settings for each model. Use these values when configuring models in Langdock.

OpenAI GPT-5.2 models

ModelAPI TypeContext SizeMax Output TokensSpecial Configuration
GPT-5.2Responses API400,000128,000Set reasoning to minimal and verbosity to low
GPT-5.2 (Thinking)Responses API400,000128,000Set reasoning to high and verbosity to low
GPT-5.2 ProResponses API400,000128,000Maximum reasoning depth and reliability

OpenAI GPT-5.1 models

ModelAPI TypeContext SizeMax Output TokensSpecial Configuration
GPT-5.1Responses API400,000128,000Set reasoning to minimal and verbosity to low
GPT-5.1 (Thinking)Responses API400,000128,000Set reasoning to high and verbosity to low
GPT-5.1 ChatResponses API128,00016,384Only available at Azure as global standard deployment in EU or through OpenAI directly

OpenAI GPT-5 models

ModelAPI TypeContext SizeMax Output TokensSpecial Configuration
GPT-5Responses API400,000128,000Set reasoning to minimal and verbosity to low
GPT-5 (Thinking)Responses API400,000128,000Set reasoning to high and verbosity to low
GPT-5 ChatResponses API128,00016,384
GPT-5 miniResponses API400,000128,000
GPT-5 nanoResponses API400,000128,000

OpenAI GPT-4.1 models

ModelAPI TypeContext SizeMax Output TokensSpecial Configuration
GPT-4.1Completion API1,047,57632,768Good for data analyst (CSV/Excel files)
GPT-4.1 miniCompletion API1,047,57632,768
GPT-4.1 nanoCompletion API1,047,57632,768

OpenAI GPT-4o models

ModelAPI TypeContext SizeMax Output TokensSpecial Configuration
GPT-4oCompletion API128,00016,384
GPT-4o MiniCompletion API128,00016,384

OpenAI reasoning models

ModelAPI TypeContext SizeMax Output TokensSpecial Configuration
o3Responses API200,000100,000
o3 MiniCompletion API200,000100,000Use model ID o3-mini
o3 Mini highCompletion API200,000100,000Use model ID o3-mini and set reasoning effort to high
o4 MiniResponses API200,000100,000
o4 Mini highResponses API200,000100,000Use model ID o4-mini and set reasoning effort to high
o1Completion API200,000100,000

Anthropic Claude models

ModelAPI TypeContext SizeMax Output TokensSpecial Configuration
Claude Opus 4.6Completion API200,000128,000
Claude Opus 4.6 ReasoningCompletion API200,000128,000Enable Display Thinking
Claude Opus 4.5Completion API200,00064,000
Claude Opus 4.5 ReasoningCompletion API200,00064,000Enable Display Thinking
Claude Sonnet 4.6Completion API200,00064,000
Claude Sonnet 4.6 ReasoningCompletion API200,00064,000Enable Display Thinking
Claude Sonnet 4.5Completion API200,00064,000
Claude Sonnet 4.5 ReasoningCompletion API200,00064,000Enable Display Thinking
Claude Sonnet 4Completion API200,00064,000
Claude Sonnet 4 ReasoningCompletion API200,00064,000Enable Display Thinking
Claude Sonnet 3.7Completion API200,0008,192
Claude Sonnet 3.7 ReasoningCompletion API200,0008,192Enable Display Thinking
Claude Haiku 4.5Completion API200,00064,000

Google Gemini models

ModelAPI TypeContext SizeMax Output TokensSpecial Configuration
Gemini 2.5 ProCompletion API1,000,00064,000Supports reasoning/thinking
Gemini 2.5 FlashCompletion API1,000,00032,000Supports reasoning/thinking
Gemini 3 ProCompletion API1,000,00064,000
Gemini 3 FlashCompletion API200,00032,000

Other models

ModelAPI TypeContext SizeMax Output TokensSpecial Configuration
Mistral Large 2411Completion API128,000No image analysis support
CodestralCompletion API32,000Code generation model
Llama 4 MaverickCompletion API1,000,000
Llama 3.3 70BCompletion API128,000No image analysis support
DeepSeek R1Completion API128,000US region only, no tool support
DeepSeek v3Completion API128,000
Amazon Nova LiteCompletion API300,000US region only
Amazon Nova ProCompletion API300,0005,000US region only
For the most up-to-date model information and capabilities, check the model picker in app.langdock.com.

Special cases during setup

Mistral from Azure: Make sure to select “Mistral” as the SDK. Claude from AWS Bedrock: When you select the Bedrock SDK, the “Base URL” field becomes “Access Key ID” and the “API Key” field becomes “Secret Access Key”. Enter your AWS credentials in these fields. See the Bedrock setup guide for details. Flux from Replicate: The base URL field needs to have the full model path, not just the base URL. For Flux 1.1 Pro this is: https://api.replicate.com/v1/models/black-forest-labs/flux-1.1-pro/predictions