كتالوج النماذج

Google's newest default — frontier smarts at a Flash price.

Google's open-weight model — near-free tokens for bulk work.

The fastest, cheapest Gemini of the 3rd series.

NVIDIA's open reasoning flagship, available free through AnyModel.

The fast, light GPT-5.6 — cheap agents and high-volume coding.

Latest frontier agentic coding model — the new Codex default.

Balanced agentic coding model for everyday work.

Production workhorse — near-flagship quality at half the price.

The strongest mini — cheap sub-agents and high-volume tasks.

OpenAI's flagship for coding, agents and research-grade reasoning.

xAI's current frontier model — its own docs' default pick for code.

Grok's coordinated multi-agent mode for deep research.

The balanced Claude — fast, smart, affordable.

Anthropic's Mythos-class tier above Opus — #1 on our AI Arena.

Cheapest, fastest Claude for high-volume tasks.

Previous-generation Opus — flagship quality, smaller multiplier.

Previous Opus — between 4.8 and 4.6 in the metering ladder.

The current Opus — Anthropic's agentic-coding flagship.

The newest experimental Opus, served through Kiro.

The new mid-tier Claude 5 — intro-priced by the vendor until September.

Zhipu's MIT-licensed flagship — a coding-agent favourite.

The cheapest serious reasoner on the market.

Open-weight frontier reasoning at rock-bottom prices.

Efficient Qwen MoE model with low input cost.

Moonshot's multimodal flagship for coding, games and knowledge work.

Moonshot's strongest coder, always-thinking.

Long-context multimodal reasoning at a budget price.

Free Models Auto Router

Automatically selects a currently available free model.