AI Models, Explained Clearly

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

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

A low-cost image model for trying visual ideas quickly, from social graphics to photo concepts.

Typical price basis

$0.007 / image

Maximum output

1K raster output; no 2K or SVG variant

Google's speech-generation model for expressive narration, character voices and dialogue in 130 languages.

Price basis

$0.50 text input · $9 audio output / 1M tokens

Interaction mode

Text-to-speech with two-speaker dialogue

Google's lower-cost speech-generation model for read-aloud features and high-volume audio in 101 languages.

Price basis

$0.50 text input · $6 audio output / 1M tokens

Interaction mode

Text-to-speech with two-speaker dialogue

An OpenAI model for coding projects and assistants that carry out several steps with tools.

Context window

1.05M tokens

Maximum output

128K tokens

A low-cost OpenAI model for focused tasks repeated at scale, such as extraction, classification and short replies.

Context window

1.05M tokens

Maximum output

128K tokens