AI Models, Explained Clearly

Grok's realtime voice model for spoken conversations, customer support and assistants that can use tools during a call.

Price basis

$0.08 / audio minute

Interaction mode

Realtime speech-to-speech with tools

Google DeepMind's open-weight embedding model for local search across text, code, images, audio, and video.

Embedding price

Open weights; self-hosted

Input capacity

8,192 shared tokens across text and media

Google's Gemini 4 model for coding, research and tasks involving large collections of text, images, audio or video.

Context window

1,048,576 tokens shared by input, thinking and output

Maximum output

65,536 synchronous; long decode uses the remaining context

Meta's model for extended coding projects, research and agents that work across files and tools.

Context window

1,048,576 tokens

Maximum output

Not published

A separate Muse Wonder variant for demanding coding work inside a paid Muse Code plan.

Context window

1M tokens

Maximum output

Not published

Microsoft's decision model for sorting requests, choosing a route and scoring results without generating a chat response.

Input price

$0.042 / 1M input tokens; output free

Input capacity

32,768 tokens

Cloudflare's larger decision model for classifying information and choosing an action without generating a chat response.

Input price

$0.24 / 1M input tokens

Input capacity

65,536 tokens; up to 64 questions per request

A smaller Cloudflare decision model for frequent routing and classification tasks, with a lower input-token price than Clef.

Input price

$0.038 / 1M input tokens

Input capacity

24,576 tokens on Workers AI; up to 64 questions per request

An OpenAI reasoning model for complex coding, research and tool-assisted work at a lower token price than Astra.

Context window

1.05M tokens

Maximum output

128K tokens

An expressive text-to-speech model for narration, character voices and dialogue in many languages.

Price basis

$0.08 / 1,000 characters

Interaction mode

Text-to-speech and multi-speaker dialogue

A low-latency speech model for assistants and interactive characters that need an expressive speaking voice.

Price basis

$0.04 / 1,000 characters

Interaction mode

Realtime text-to-speech / text-to-dialogue

A Claude model for everyday coding, writing and visual analysis, with room for large reference documents.

Context window

1M tokens

Maximum output

128K tokens