The model is the brain of your Agent. Choosing the right one—and configuring it properly—determines how well your Agent reasons, how fast it responds, and how much it costs to run.Documentation Index
Fetch the complete documentation index at: https://docs.getcargo.ai/llms.txt
Use this file to discover all available pages before exploring further.
.png?fit=max&auto=format&n=hIRoZCuwMytQmSWF&q=85&s=bc99f15e40dfc606ebe9f043c44538ff)
Selecting a model
Cargo supports leading LLM providers:| Provider | Models | Strengths |
|---|---|---|
| OpenAI | GPT-4o, GPT-4o-mini | Excellent reasoning, broad capabilities, reliable |
| Anthropic | Claude 3.5 Sonnet, Claude 3 Opus | Strong reasoning, nuanced responses, good at following instructions |
| Gemini Pro, Gemini Flash | Fast, cost-effective, good for simpler tasks |
How to choose
| Task complexity | Recommended approach |
|---|---|
| Complex analysis (qualification, research synthesis) | Use a powerful model (GPT-4o, Claude Opus) |
| Simple classification (routing, tagging) | Use a faster model (GPT-4o-mini, Gemini Flash) |
| High volume, low stakes | Prioritize speed and cost |
| Low volume, high stakes | Prioritize reasoning quality |
Behavioral parameters
Reasoning Steps
The maximum number of logical sub-tasks the Agent can perform to reach a conclusion.| Setting | Effect | Use when |
|---|---|---|
| Low (1-3) | Fast, direct responses | Simple lookups, single-action tasks |
| Medium (4-6) | Balanced reasoning | Most standard workflows |
| High (7+) | Deep, multi-step problem solving | Complex research, multi-source synthesis |
Temperature
Controls the creativity and variability of outputs.| Temperature | Behavior | Best for |
|---|---|---|
| 0.0 - 0.2 | Deterministic, precise, consistent | Data extraction, classification, CRM updates |
| 0.3 - 0.6 | Balanced creativity | General tasks, qualification, research |
| 0.7 - 1.0 | Creative, varied | Copywriting, brainstorming, conversational engagement |
- Lower temperature → reproducible results
- Higher temperature → more varied, human-like responses
Configuration examples
Lead Qualification Agent
Model: GPT-4o
Reasoning Steps: 4
Temperature: 0.2Needs good reasoning but consistent, reliable outputs.
Reasoning Steps: 4
Temperature: 0.2Needs good reasoning but consistent, reliable outputs.
Account Research Agent
Model: Claude 3.5 Sonnet
Reasoning Steps: 6
Temperature: 0.4Requires deeper research and synthesis across sources.
Reasoning Steps: 6
Temperature: 0.4Requires deeper research and synthesis across sources.
Email Drafting Agent
Model: GPT-4o
Reasoning Steps: 3
Temperature: 0.7Needs creativity for engaging, personalized copy.
Reasoning Steps: 3
Temperature: 0.7Needs creativity for engaging, personalized copy.
Simple Router Agent
Model: GPT-4o-mini
Reasoning Steps: 2
Temperature: 0.1Fast classification with minimal reasoning needed.
Reasoning Steps: 2
Temperature: 0.1Fast classification with minimal reasoning needed.
Optimizing for cost and speed
Once your Agent works correctly, consider:- Reduce reasoning steps if tasks complete in fewer steps
- Try a faster model (like GPT-4o-mini) and verify quality remains acceptable
- Lower temperature for more predictable outputs
- Limit resources to reduce context size and processing time