Supported Models for Prompt Optimization

Prompt optimization (GEPA and MIPRO) supports policy models from multiple providers:

OpenAI Models

• gpt-5
• gpt-5-mini
• gpt-5-nano
• gpt-4o
• gpt-4o-mini

Note: gpt-5-pro is explicitly rejected (too expensive: $15/$120 per 1M tokens)

Groq Models

• openai/gpt-oss-20b
• openai/gpt-oss-120b
• moonshotai/kimi-k2-0905
• meta/llama-guard-4-12b
• qwen/qwen3-32b
• meta/llama-3.3-70b-versatile
• meta/llama-3.1-8b-instant

See Prompt Optimization Configuration for complete details on policy, mutation, and meta models.