Choosing the Right Model
The Cosine CLI gives you access to a range of AI models. Each has different characteristics in terms of speed, cost, reasoning depth, and output style. Over time, you’ll develop your own preferences — but here’s a practical starting point.
Model Characteristics at a Glance
Section titled “Model Characteristics at a Glance”| Model | Speed | Cost | Best for |
|---|---|---|---|
| Codex | Fast | Medium | General coding, everyday tasks |
| Codex Spark | Very fast | Low | Quick edits, fast lookups |
| Sonnet | Medium | Medium | Creative writing, prose, nuanced output |
| Opus | Slow | High (3×) | Deep reasoning, complex multi-step tasks |
| Gemini (various) | Slow | Varies | Alternative perspective, large context tasks |
| Kimi | Very fast | Low | Quick first drafts, throwing ideas at the wall |
| MiniMax | Fast | Low | Rapid iteration |
Practical Defaults
Section titled “Practical Defaults”If you’re not sure which model to use, these are solid defaults:
- Codex on High reasoning — great all-rounder for tasks involving code and structured thinking.
- Sonnet on Medium reasoning — better for writing tasks, prose, and anything where tone and nuance matter.
You don’t need to optimise aggressively across models. The long-term goal is that model selection becomes increasingly automatic. For now, defaulting to Codex or Sonnet for most tasks is a reliable approach.
When Speed Matters
Section titled “When Speed Matters”If you’re in the middle of a task and need a quick answer or small edit without interrupting your flow, switch to a faster model like Kimi or Codex Spark. Fast models are great for:
- Sanity-checking a quick idea
- Small, well-defined code changes
- Getting a first draft to react to
When Quality Matters More Than Speed
Section titled “When Quality Matters More Than Speed”For complex multi-step tasks running in the background — especially in Swarm Mode — the extra time a larger model takes is worth it. Use Opus or Codex on High when:
- You’re producing something that needs to be good the first time
- The task involves deep reasoning or multiple interdependent decisions
- You’re running it in the background anyway and won’t be waiting
Models and Personas
Section titled “Models and Personas”Different models have genuinely different characteristics — not just in capability, but in style and “feel.” Some users find Claude models (Sonnet, Opus) produce more visually pleasing HTML and more natural-sounding prose. Codex models tend to be more precise and structured.
Running the same task with two different models in parallel (one as the main agent, one as a fresh session with no context) is a useful technique for getting varied perspectives on the same problem.
Key Takeaways
Section titled “Key Takeaways”- Codex on High or Sonnet on Medium are good everyday defaults.
- Use fast models (Kimi, Codex Spark) for quick in-flow tasks.
- Use larger models (Opus, Codex on High) for complex background tasks.
- You’ll build your own preferences over time — but don’t over-optimise early.