Configuring LLM Models
- How to select a platform and model for your LLM agent
- What the General tab settings do
- How to fine-tune temperature, token limits, and other options on the Advanced tab
When you set an agent's Assistant Type to llm, AutoTalk reveals the model configuration options. The first thing you choose is the AI platform, then you configure the model and its behavior.
Selecting a platform
The Platform type field determines which AI provider powers your agent. AutoTalk supports these managed providers and custom endpoint options:
| Platform | Description |
|---|---|
| openai (default) | OpenAI models including GPT-5.5, GPT-5.4, GPT-4.1, and others. |
| deepseek | DeepSeek models including DeepSeek V4 Flash and V4 Pro. |
| gemini | Google Gemini models including Gemini 3.1 Flash-Lite and Gemini 2.5 models. |
| anthropic | Anthropic Claude models including Opus, Sonnet, and Haiku. |
| openrouter | Route requests through OpenRouter by entering a provider-prefixed model ID. |
| custom | Connect to a custom or third-party API endpoint. Use this for providers not listed above, or for your own fine-tuned models served through a compatible API. |
After selecting a platform, five configuration tabs appear: General, Messages, Actions, Tools, and Advanced. This page covers the General and Advanced tabs; see System Messages and Tools for the others.
General tab settings
The General tab contains the platform, model, and API token.
Model
Select the specific model to use from a dropdown list. Each model displays:
- A cost badge (Low cost, Medium, or High cost), derived from where the model's combined input + output price falls among the available models
- Pricing per 1K tokens for both input and output, so you can estimate costs
Lighter models cost less but may produce lower-quality responses; heavier models cost more but handle complex conversations better. Deprecated models remain visible for existing agents but are marked in the picker; choose a current stable model for new agents.
Token
A searchable field where you can select an existing API token or create a new one. This token authenticates your agent with the chosen AI platform. If you have not yet added an API key for the platform, you can create one directly from this field.
Note: The Token field is conditionally hidden. It appears only when you use the openrouter platform, or when you turn on the Enable BYO API key toggle — also on the General tab — for a managed provider. With BYOK off on a managed provider (openai, deepseek, gemini, anthropic), AutoTalk supplies its own platform key, so no Token field is shown.
Advanced tab settings
Temperature, token limits, and the optional behavior toggles live on the Advanced tab, grouped into sections.
Temperature
Under the Behavior section. Controls how creative or deterministic the model's responses are. The default value is 1.
- Lower values (0.0 to 0.5): The agent gives more focused, predictable, and consistent answers. Best for factual customer support.
- Higher values (0.8 to 1.5): The agent produces more varied and creative responses. Useful for brainstorming or casual conversation, but may reduce accuracy.
Some models do not support temperature — notably the GPT-5 family (gpt-5.5, gpt-5.4, gpt-5.4-mini, gpt-5.4-nano), which ignore it. For those models the temperature control is disabled in the form.
Agent loop
Under the Behavior section (shown on every platform). When Enable agent loop is checked (off by default), the agent can run several tool-call rounds automatically before producing its final answer, instead of stopping after a single round. Turning it on reveals Max iterations, which caps how many loop rounds may run (default 15, range 1–50). Higher values let the agent chain more tool calls but can increase latency and cost. The agent loop is not available in Responses API mode.
API mode
Under the Behavior section, on the default openai platform. Selects how AutoTalk calls the provider: Chat Completions (default) or Responses. Chat Completions is the standard mode used by most agents. Responses uses OpenAI's Responses API, enabling features such as server-side response storage and native MCP handling; it does not support the agent loop.
Max response tokens
Under the Token limits section. Sets the upper limit on how many tokens the model can generate in a single response. Use this to control response length and cost. If left empty, the model uses its default maximum.
Max chars per message
Under the Token limits section. Limits how many characters from the user's message are sent to the model. The default is 1024 characters (maximum 2048). Increase this if your customers tend to send longer messages and you want the agent to consider the full text; decrease it to reduce costs on verbose inputs.
Enable structured outputs
Under the Structured outputs section. When checked, the model is instructed to return responses in a structured format (such as JSON). This is useful when the agent's output is consumed by another system rather than displayed directly to a customer.
Enable context token budget
Under the Context budget section. When checked, AutoTalk manages how much conversation history is sent to the model by enforcing a token budget for context. This prevents the context window from exceeding the model's limit on long conversations and helps control costs.
Enable image processing
Under the Image processing section, available only when the platform is openai. When checked, the agent can receive and process images sent by customers (on models that support vision capabilities). This allows the agent to describe, analyze, or respond to photos and screenshots.
For most customer-facing agents, start with the openai platform and choose a capable stable model like gpt-4.1 or gpt-4o-mini. If the model supports temperature (such as the GPT-4.1 / GPT-4o family), set it to 0.3 to 0.5 for reliable answers; note that GPT-5-family models (including gpt-5.4-mini) ignore temperature, so the setting does not apply to them. Leave Max chars per message at the default, and enable image processing only if your use case requires it, since it increases token usage.