In the Cascade panel Ctrl/⌘ + L, you can easily switch between different models of your choosing.

Under the text input box, you will see a model selection dropdown menu. You will see the following models available:

  • SWE-1
  • SWE-1-lite
  • GPT-4o
  • GPT-4.1
  • o3 (medium reasoning)
  • o3 (high reasoning)
  • o4-mini-medium
  • o4-mini-high
  • Claude 3.5 Sonnet
  • Claude 3.7 Sonnet
  • Claude 3.7 Sonnet (Thinking)
  • DeepSeek-V3-0324
  • DeepSeek-R1
  • Gemini 2.0 Flash
  • Gemini 2.5 Flash
  • Gemini 2.5 Pro
  • xAI Grok-3
  • xAI Grok-3 mini (Thinking)

​
Premium Models

Due to the wide variation between the serving costs of each model, depending on the model you select, each of your input prompts will consume a different number of prompt credits.

Below you will find a breakdown of how many prompt credits you will be charged for each model:

ModelPrompt creditsFreePro/TrialTeamsEnterpriseImages
SWE-10✓✓✓
SWE-1-lite0✓✓✓
GPT-4o1✓✓✓✓✓
GPT-4.10.25✓✓✓✓✓
o3 (medium reasoning)7.5✓✓✓
o3 (high reasoning)10✓✓✓
o3-mini (medium reasoning)1✓✓✓
o4-mini-medium0.25✓✓✓✓✓
o4-mini-high0.25✓✓✓✓✓
Claude 3.5 Sonnet1✓✓✓✓✓
Claude 3.7 Sonnet1✓✓✓✓✓
Claude 3.7 Sonnet (Thinking)1.25✓✓✓✓✓
DeepSeek-V3-03240✓
DeepSeek-R10.5✓
Gemini 2.0 Flash0.25✓✓✓✓✓
Gemini 2.5 Flash0.125✓✓✓
Gemini 2.5 Pro1✓✓✓✓
xAI Grok-31✓✓✓
xAI Grok-3 mini (Thinking)0.125✓✓✓

​
SWE-1

SWE-1 is our family of in-house frontier models built specifically for software engineering tasks.

Based on our internal evals, it has performance nearing that of frontier models from the foundation labs.

  • SWE-1: High-reasoning, tool-capable, and Cascade-optimized. Claude 3.5-level performance at a fraction of the cost.
  • SWE-1-lite: Replaces Cascade Base — faster, better, and free for all.
  • SWE-1-mini: Powers passive suggestions in Windsurf Tab, optimized for real-time latency.