26 frontier models. All live today.

The fastest Claude, near-frontier intelligence — 200k context, extended thinking.

Previous-gen flagship — 1M context, extended thinking. Consider migrating to Opus 4.7.

Anthropic's most capable general-purpose model — excels at complex reasoning and agentic coding, native 1M context.

Anthropic's newest flagship — further gains in complex reasoning and agentic coding, native 1M context.

Anthropic's newest flagship Claude Opus 5 — leading complex reasoning and agentic coding, native 1M context.

The best balance of speed and intelligence — 1M context, extended/adaptive thinking.

The best balance of speed and intelligence — adaptive thinking on by default, native 1M context.

OpenAI's more economical coding and professional-work model — 1M context.

OpenAI's strongest mini model — good for coding, computer use, and subagents; 400k context.

OpenAI's flagship coding and professional-work model — adjustable reasoning effort, 1M context.

Official GPT-5.6 alias — always routes to the Sol flagship tier.

OpenAI's cost-sensitive high-throughput tier (Luna) — extraction, classification and summarization workloads, 1.05M context.

OpenAI's frontier flagship (Sol tier) — complex coding and long-horizon agentic work, reasoning effort up to max, 1.05M context.

OpenAI's balanced intelligence/cost tier (Terra) — GPT-5.5-class performance at a lower price, 1.05M context.

OpenAI's native image generation and editing (/v1/images generations + edits) — supports arbitrary resolutions.

Low-latency, cost-efficient multimodal model — good for translation, transcription, document processing, and other high-frequency lightweight tasks.

Google's most intelligent model — sustained frontier performance, excels at agentic and coding tasks.

Always points to the newest Gemini Flash generation; currently equivalent to gemini-3.5-flash.

Always points to the newest Gemini Flash-Lite generation; currently equivalent to gemini-3.1-flash-lite.

Google's flagship thinking model — excels at complex code, math, and STEM reasoning; 1M context.

DeepSeek's faster, more economical API. Official DeepSeek traffic is served by the vision SKU (image understanding). Deep thinking on by default, can be disabled.

DeepSeek V4 Pro — significantly stronger agent capability and rich world knowledge; deep thinking on by default, can be disabled manually.

Zhipu's first native multimodal model in the GLM-5 series — 320B total / 18B active parameters, with image/video/file input and 1M-token context.

Kimi's flagship multimodal model (text/image/video input) with a 1M-token context window and always-on reasoning; Kimi Code defaults reasoning_effort to high.

xAI's intelligent coding model for agentic software and engineering workflows — 500k context, tunable reasoning_effort (default high).

xAI's flagship model for coding, long-horizon agents, and knowledge work — 500k context, tunable reasoning_effort (default high, including xhigh).