Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.langdock.com/llms.txt

Use this file to discover all available pages before exploring further.

Which models to add

AI models evolve quickly. We recommend adding at least one flagship model from each major provider. This gives your users access to the best available model for different tasks while keeping your setup manageable. When a provider releases a new model, add it alongside the existing one rather than replacing it. Users may have agents or workflows that rely on specific models, so removing them without notice can cause disruption. Select a provider to see the recommended model types and their configuration values.

Model-specific configuration

Use these values when configuring models manually. With a prebuilt Langdock config, these are applied automatically.
Add these model types:
  • Latest flagship - Most capable for complex tasks
  • Efficient variant (mini/nano) - Fast, cost-effective for everyday use
  • Reasoning model (o-series) - For analytical and mathematical tasks
Look for the highest version number available. OpenAI increments version numbers with each major release.

GPT-5.2

ModelAPI TypeContext SizeMax
Output Tokens
Special
Configuration
GPT-5.2Responses API400,00032,000Reasoning: minimal, verbosity: low
GPT-5.2 (Thinking)Responses API400,00032,000Reasoning: high, verbosity: low
GPT-5.2 ProResponses API400,00032,000Max reasoning depth

GPT-5.1

ModelAPI TypeContext SizeMax
Output Tokens
Special
Configuration
GPT-5.1Responses API400,00032,000Reasoning: minimal, verbosity: low
GPT-5.1 (Thinking)Responses API400,00032,000Reasoning: high, verbosity: low
GPT-5.1 ChatResponses API128,00016,000Azure EU global deployment or OpenAI only

GPT-5

ModelAPI TypeContext SizeMax
Output Tokens
Special
Configuration
GPT-5Responses API400,00032,000Reasoning: minimal, verbosity: low
GPT-5 (Thinking)Responses API400,00032,000Reasoning: high, verbosity: low
GPT-5 ChatResponses API128,00016,000\u2014
GPT-5 miniResponses API400,00016,000\u2014
GPT-5 nanoResponses API400,00016,000\u2014

GPT-4.1

ModelAPI TypeContext SizeMax
Output Tokens
Special
Configuration
GPT-4.1Completion API1,047,57632,000Good for data analysis
GPT-4.1 miniCompletion API1,047,57632,000\u2014
GPT-4.1 nanoCompletion API1,047,57632,000\u2014

GPT-4o

ModelAPI TypeContext SizeMax
Output Tokens
Special
Configuration
GPT-4oCompletion API128,00016,000\u2014
GPT-4o MiniCompletion API128,00016,000\u2014

Reasoning models (o-series)

ModelAPI TypeContext SizeMax
Output Tokens
Special
Configuration
o3Responses API200,00032,000\u2014
o3 MiniCompletion API200,00032,000Model ID: o3-mini
o3 Mini highCompletion API200,00032,000Model ID: o3-mini and set reasoning effort to high
o4 MiniResponses API200,00032,000\u2014
o4 Mini highResponses API200,00032,000Model ID: o4-mini, effort: high
o1Completion API200,00032,000\u2014
For the most up-to-date model information and capabilities, check the model picker in app.langdock.com. Model naming follows consistent patterns across providers — see our Model Guide for help understanding these patterns.