Overview
ModelStack provides access to models from three leading AI providers through a single API. All models use the OpenAI-compatible chat completions format.Versioned model variants (e.g.,
claude-sonnet-4-5-20250929) are also supported. Any model with a supported prefix (claude-, gpt-, o1-, o3-, o4-, gemini-) is accepted.Anthropic
Versioned variants also supported:
claude-opus-4-5-20251101, claude-opus-4-1-20250805, claude-sonnet-4-5-20250929, claude-sonnet-4-20250514, claude-opus-4-20250514, claude-haiku-4-5-20251001
OpenAI
Versioned variants also supported:
gpt-4o-2024-11-20, gpt-4o-mini-2024-07-18
Model Selection Guide
Best Quality
claude-opus-4-1 or o1 — Most capable models for complex reasoning, code generation, and nuanced tasks.Best Balance
claude-sonnet-4-5 or gpt-4o — Excellent quality at moderate cost. Great for production workloads.Best Speed
gemini-2.5-flash or gpt-4o-mini — Fast responses at low cost. Ideal for high-volume, latency-sensitive tasks.Best Value
gemini-2.0-flash-lite or claude-3-haiku-20240307 — Lowest cost per token for budget-conscious applications.