Reference

LLM Models

Lists supported LLM providers and models in Stubber. Useful for choosing OpenAI, Anthropic Claude, Google Gemini, and other model options for AI tasks.

# Stubber Model Aliases

Stubber maintains a set of model aliases — stable names that always point to a specific, high-quality model chosen by Stubber. Instead of committing to a particular model version, you can use an alias and Stubber will keep it pointed at the best available option as models evolve.

You use an alias exactly like any other model name in the GPT Chat Task.

# Current Aliases

When Stubber updates an alias to a newer or better model, this happens transparently — your templates continue working without any changes.

# OpenAI

Depending on the model, Stubber uses either the OpenAI Chat Completions API or the newer Responses API — whichever works best for that model. The gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna, gpt-6-sol, gpt-6-luna, and gpt-6.1-sol models use the Responses API. All other OpenAI models use the Chat Completions API.

OpenAI models are used with their standard API format with the following modifications:

# O-Type Models

• o3-mini and o4-mini: We delete the temperature field as these models don't support it
• All O-type models: We convert image URLs into data URIs (some O-type models do not support images at all, e.g., o3-mini)

# OpenAI Models

# Anthropic (Claude)

Anthropic models require specific message format conversions:

# Message Processing

• Consecutive roles: Anthropic does not support consecutive roles, so we combine consecutive role messages into a single message with the messages.content into an array of the messages
• System messages: The system messages are extracted and concatenated to be a single top-level system message parameter as Anthropic does not support system messages in the conversation flow
• Conversation start: Anthropic calls have to start with a user message. If it doesn't start with one, we inject a simple one that just says "hi"

# Image Understanding

For Anthropic, Stubber accepts the normal OpenAI specification of image understanding messages:

Before these messages are sent to Anthropic, we convert them to their structure, which can be seen here.

# Claude Models

# Removed Models

The following Claude-3 models have been removed by the provider:

• claude-3-haiku-20240307 - Removed by Anthropic
• claude-3-sonnet-20240229 - Removed by Anthropic
• claude-3-opus-20240229 - Removed by Anthropic

# Google Gemini

Gemini models have specific requirements and limitations:

# Message Processing

• System message limitation: Gemini models cannot be used with only a system message - they require at least one user message
• Image processing: We convert image URLs into data URIs for compatibility

# Gemini Models

# Cerebras

Cerebras models use the OpenAI API integration with the following limitation:

# Empty Enums

• Empty enum limitation: Cerebras models do not support empty enums, so select fields with no options will result in errors.

# Cerebras Models

# DeepSeek

DeepSeek models use the OpenAI API integration with the following behavior:

# DeepSeek Reasoner

• deepseek-reasoner: Does not support function calling. If you pass tools to this model, it will automatically switch to deepseek-chat for that request

# DeepSeek Models

# Moonshot AI

Moonshot AI models use the OpenAI API integration.

# Moonshot AI Models

# Meta

Meta models use the OpenAI API integration.

# Meta Models

# Other Providers

# Additional Models

# General Operations Applied to All Providers

# Function Method Determination

We determine which function method to use based on the model and the provider:

• Models released after May 2025: Default to supplying functions to providers as tools
• Models released before May 2025: Default to supplying functions to providers as functions

This is mostly abstracted for users and they do not need to worry about it, but you can specify a specific function method for a model as a parameter (see function_method).

If a specific chat already had a function call following a specific function method, then future iterations of that chat will also use that same function method. For example, if you use a new model (which uses tools) and then switch to an older function type model in the same chat, the older function type model would also use tools.

# Tool Result Injection

For tools, tool messages from LLMs must be followed by a tool result. If there is a scenario where users disable dynamic tasks (which we use to inject tool results after function calls), then Stubber will inject a simple tool result of:

# TypeSafe (System One)

System One models evaluate a state against structured questions and return typed answers — choices, scores, and probabilities. They are used with the System One Model Call task, not the GPT Chat Task.

# System One Models

# Image Generation Models

These models are available in the Generate Image Task.

# All Supported Chat Models

The following table shows all supported chat models and their capabilities: