Skip to main content

Models

Models are the LLM options available in Aegis. Each has a URL-safe slug (what you pass in model_slug on runs and evaluations), a display name, and supplier metadata. Thinking models may also accept a reasoning_level on evaluate and run creation — allowed values are per model (see tables below). When you omit model_slug on those endpoints, the default is gpt-5.6-luna with reasoning level none.

There is no GET /models (or related) route on the API server—the catalog is documented here.

OpenAI

slugnamethinkinglatestreasoning_levelsdefault_reasoning_level
gpt-4oGPT-4onono
gpt-4.1GPT-4.1nono
o3-minio3-miniyesno
o4-minio4-miniyesno
gpt-5GPT-5yesnominimal, low, medium, highmedium
gpt-5.1GPT-5.1yesnonone, low, medium, highnone
gpt-5.2GPT-5.2yesnonone, low, medium, high, xhighnone
gpt-5.4GPT-5.4yesnonone, low, medium, high, xhighnone
gpt-5.5GPT-5.5yesnonone, low, medium, high, xhighnone
gpt-5.6-lunaGPT-5.6 Lunayesyesnone, low, medium, high, xhigh, maxnone
gpt-5.6-terraGPT-5.6 Terrayesyesnone, low, medium, high, xhigh, maxnone
gpt-5.6-solGPT-5.6 Solyesyesnone, low, medium, high, xhigh, maxnone

Anthropic

slugnamethinkinglatestreasoning_levelsdefault_reasoning_level
claude-haiku-4-5Claude Haiku 4.5nono
claude-sonnet-4-6Claude Sonnet 4.6yesnolow, medium, high, maxmedium
claude-sonnet-5Claude Sonnet 5yesyeslow, medium, high, maxmedium
claude-opus-4-5Claude Opus 4.5yesno
claude-opus-4-6Claude Opus 4.6yesnolow, medium, high, maxmedium
claude-opus-4-7Claude Opus 4.7yesnolow, medium, high, xhigh, maxmedium
claude-opus-4-8Claude Opus 4.8yesyeslow, medium, high, xhigh, maxmedium
claude-opus-5Claude Opus 5yesyeslow, medium, high, maxmedium
  • thinkingyes means the model is treated as a “thinking” / reasoning-style model in the product; no means it is not.
  • latestyes marks the current recommended variant within that supplier’s line where applicable; other rows show no. A supplier may have more than one latest model (for example a fast and a flagship option).
  • reasoning_levels — allowed values for reasoning_level on evaluate and run endpoints. means the model does not accept a reasoning level (omit the field; supplying one returns 400).
  • default_reasoning_level — value used when reasoning_level is omitted on a model that supports it. when not applicable.

In API payloads, always use the slug (for example gpt-5.6-luna, gpt-5.2, or claude-sonnet-5).