Model benchmarks

Choose the right QFOXAI model for each job

Use branded model aliases for production integrations. Choose a lighter model for everyday automation, a balanced model for general chat, or an advanced QFOXAI route for deeper reasoning while private provider names stay internal.

View plans API docs

Current routing mode: BALANCED. Benchmarks use recent platform telemetry where available and public branded model aliases only.

Default Chat API All users

QFOXLITE

LITE

Best for: Fast replies, support drafts, routing, and high-volume automation.

Latency34,418 ms avg

Cost$0.001 / 1K mixed tokens

30D Calls33

30D Tokens130,136

Chat API All users

QFOXAI

Branded QFOXAI model for chat and OpenAI-compatible API usage.

Best for: Balanced chat, API, business writing, summaries, and internal tools.

Latency25,090 ms avg

Cost$0.002 / 1K mixed tokens

30D Calls2,081

30D Tokens3,169,334

Chat API Subscribed users

QFOXPRO

Premium QFOXAI model alias for deeper reasoning, longer answers, and higher-value API usage.

Best for: Complex reasoning, stronger writing, coding, analysis, and premium workflows.

Latency38,531 ms avg

Cost$0.009 / 1K mixed tokens

30D Calls4

30D Tokens14,336