Models

OpenAI's efficient reasoning model for focused tasks and everyday assistance, suited to frequent requests and concise answers.

Z.ai's multimodal coding model, tuned for long-running agent work and visual verification across complex projects.

OpenAI's reasoning model for complex software changes and sustained professional work, with clear explanations and room to iterate.

Anthropic's concise reasoning model for complex coding projects and research, with clear progress reports during long-running work.

DeepSeek's fast multimodal reasoning model, built for responsive agent work that still benefits from careful, step-by-step problem solving.

OpenAI's most capable model — built for the hardest end-to-end work across code, browsers, and documents, where careful execution matters more than cost.

Anthropic's most capable model — reserved for the hardest, highest-stakes reasoning and long-horizon agentic work where you want the strongest possible result.

xAI's flagship for long-running agentic work, coding, and ambitious visual projects — a strong choice for sustained, multi-step tasks.

Moonshot's flagship for long-horizon coding and knowledge work — patient with large contexts and especially strong on visual, interactive projects.

Anthropic's strongest everyday model. Near-Opus reasoning for coding, agents, and professional work when you want quality at Sonnet cost.

Google's flagship chat model. Quick and capable across long prompts — a strong everyday pick when responsiveness matters.

ByteDance's modern generalist for lifelike image generation, polished composition, and strong prompt adherence across creative work.

Google's fastest current image model for inexpensive drafts, consistent characters, responsive edits, and everyday creative work.

A design-focused image model with expressive illustration, clean composition, and a broad set of canvas sizes.

Google's flagship image model. Strong on photorealism and natural edits, with quick turnaround — a sharp everyday pick.

OpenAI’s image model for everyday creative work, clear lettering, and quick iteration on product visuals and illustrations.

OpenAI’s image model for detailed creative briefs, polished campaign artwork, and product imagery that needs precise visual control.

A fast, cost-conscious video model for short text- or image-guided clips, motion studies, and rapid iteration.

An image-to-video model with built-in audio. Cinematic motion suitable for short narrative clips and animation tests.

MiniMax's premium text-to-video model for cinematic clips with consistent subjects, expressive motion, and synchronized audio.

A narrative text-to-video model for longer shots with native audio, multi-shot prompting, and cinematic scene progression.

Creates short clips from text or a starting image, with generated audio and an editing path pending verification.

Google's high-quality fast video model for polished clips with frame guidance and optional synchronized audio.

Expressive preset-voice speech with five voices, controllable pacing, language guidance, and MP3 or WAV output.

AssemblyAI's accuracy-focused option. Reliable names, dates, and formatting — pick when getting the words right matters more than speed.