Models

Models Overview

AI models available through SoxAI and how routing works

Models

SoxAI gives you access to models from multiple providers through a single API endpoint. All models are accessed using the same OpenAI-compatible interface.

Model Categories

Category	Use Cases	Example Models
Chat	Conversations, Q&A, code generation, analysis	`gpt-5.4`, `claude-sonnet-4-6`, `gemini-2.5-pro`
Embeddings	Semantic search, RAG, clustering	`gemini-embedding-001`
Image Generation	Creating images from text descriptions	`gpt-image-1.5`, `gemini-2.5-flash-image`
Legacy Completion	Backward-compatible `/v1/completions` shape	any chat model — the gateway transforms internally

Choosing a Model

For general-purpose tasks:

gpt-5.4 — Best overall quality from OpenAI
claude-opus-4-7 — Top Anthropic reasoning; claude-sonnet-4-6 for balanced daily use
gemini-2.5-pro — Long-context favorite from Google

For cost-sensitive applications:

gpt-5.4-mini — Great quality at a fraction of the flagship cost
gemini-2.5-flash-lite — Very fast and inexpensive
MiniMax-M2.7 — Competitive quality at low cost

For embeddings:

text-embedding-3-small — Best cost/quality ratio for most use cases
text-embedding-3-large — Maximum accuracy for critical applications

Next Steps

Supported Models — Full list with pricing and context windows
Provider Routing — How SoxAI routes requests across providers

Rate Limits

How rate limiting and quota enforcement works in SoxAI

Supported Models

Current list of AI models available through SoxAI — Claude 4.x, GPT-5.x, Gemini 2.5/3.x, GLM 5.x, MiniMax M2.x, and Gemma. Use the model ID exactly as shown.

On this page

Models Model Categories Choosing a Model Next Steps