The model library

Anthropic

Frontier-quality text and reasoning through one OpenAI-compatible endpoint.

text

Anthropic

Fast, cheap frontier-family model for high-volume tasks.

text

Anthropic

The frontier tier for the hardest reasoning and agentic work.

text

OpenAI

OpenAI's flagship, one key away.

text

Google

Google's current fast model, million-token context.

text

Google

The previous stable Flash, still current for most work.

text

Google

Google's stable Pro tier, the non-preview reasoning model.

text

Google

Long-context workhorse on the stable 2.5 line.

text

Google

Google's newest Pro tier, shipped as a preview.

text

Google

The Gemini 3 Flash preview line.

text

Anthropic

Anthropic's first Mythos-class model, the new flagship tier above Opus, tuned for the hardest reasoning and agentic work.

text

Anthropic

The Claude 5 generation's deep-work model, maximum-capability reasoning for research, architecture, and hard agentic tasks.

text

DeepSeek

The heavyweight of the V4 family, deeper reasoning than base V4 while keeping open-weight commodity pricing.

text

DeepSeek

The V4 family's speed tier, near-V4 quality on everyday calls at the lowest price in the family.

text

xAI

xAI's flagship, half-million-token context.

text

xAI

The previous flagship, same rate card.

text

xAI

Million-token context at roughly half the flagship rate.

text

Z.ai

Z.ai's open-weight frontier challenger, strong coding and reasoning with one of the best free tiers in class.

text

Moonshot AI

Moonshot's value tier, K3-style agentic tool-calling at half the price, a favorite for high-volume agent loops.

text

Moonshot AI

Agentic coding model with strong multi-step tool use.

code