Skip to navigation
Guides

Model Selection

Pick the best model for research synthesis

The model parameter on POST /research lets you choose which LLM synthesizes the final answer. If you omit it, Caesar automatically selects a model based on your query.

Start by omitting model to let Caesar auto-select. Set model when you need consistent output, a specific latency profile, or a fixed provider.

Supported models

ModelProviderSummary
gpt-5.2OpenAIHighest quality synthesis for complex, multi-step research tasks
gemini-3.8-flashGoogleDefault model for deep research, served through Vertex AI
gemini-3.1-proGoogleBackward-compatible alias for gemini-3.8-flash
gemini-3-proGoogleAdvanced reasoning with strong long context performance
gemini-3-flashGoogleBest performance for high-volume, low-latency research
claude-opus-4.6AnthropicStrongest Claude-tier synthesis quality for long-form, nuanced analysis

Prefer gemini-3.8-flash for new integrations. Existing requests using gemini-3.1-pro remain accepted and now route to gemini-3.8-flash through Vertex AI. gemini-3-pro continues to select its existing model.

The model parameter controls research synthesis. Retrieval and source gathering remain the same.

When to use each model

gpt-5.2

Best for

  • Complex, multi-step reasoning
  • Cross-domain technical synthesis
  • High-stakes decisions that need the strongest accuracy

Trade-offs

  • Typically higher latency than Flash-tier models
gemini-3.8-flash

Best for

  • Deep analysis in code, math, or STEM topics
  • Long-context synthesis over large documents or datasets
  • Deep research using Caesar’s default Gemini model

Trade-offs

  • Requests using the legacy gemini-3.1-pro name use this same model
gemini-3-flash

Best for

  • Large scale processing and batch research
  • Low latency, high volume workloads
  • Agentic or iterative tasks that need fast turns

Trade-offs

  • Less depth than Pro or Opus on very complex analysis
claude-opus-4.6

Best for

  • Maximum Claude-tier synthesis quality
  • Highly nuanced argumentation and editorial polish
  • Long-form outputs where tone and structure matter

Trade-offs

  • Higher latency than Flash-tier and many non-Opus models

Example

{
  "query": "Compare major approaches to carbon capture and their performance",
  "model": "gemini-3-flash",
  "reasoning_loops": 2
}

Quick picker

GoalRecommended model
Fast, high volume researchgemini-3-flash
Deep research with Geminigemini-3.8-flash
Maximum accuracy on complex researchgpt-5.2
Maximum Claude-tier writing qualityclaude-opus-4.6

Learn more