Senova · Models

Pick the right Senova model

Five language models and one image model, each tuned for a different kind of work. They run locally in the Senova app, or in the cloud through third-party model providers. This page also shows the proposed prices for a hosted Senova API.

Proposed prices

The hosted Senova API is not available yet. The prices below are proposed list prices and may change before launch. See the proposed subscription plans too.

Choose by task

Senova Suite 1

Default

Well-rounded and the one to start with. Writes and fixes code, explains, plans, and reads images and screenshots.

Vision
Tools
Thinking
Fast

Input / 1M: $0.25
Output / 1M: $1.50

Senova Symphony 1

Most capable

Our strongest reasoning. Use it for hard bugs, architecture decisions and long careful answers. Slower and pricier. Symphony runs on open models we select and tune.

Tools
Thinking
Moderate speed

Input / 1M: $0.75
Output / 1M: $3.75

Senova Fugue 1

For agents

Built for coding agents: long runs of tool calls, file edits and shell commands without losing the thread.

Tools
Thinking
Fast

Input / 1M: $0.20
Output / 1M: $0.90

Senova Prelude 1

Fastest

Quick answers and everyday code at the lowest price. Good for high-volume and latency-sensitive work.

Tools
Adjustable thinking
Fastest

Input / 1M: $0.10
Output / 1M: $0.50

Senova Étude 1

Light

Small, quick edits: renames, formatting, short fixes and simple questions.

Tools
Thinking
Fast

Input / 1M: $0.12
Output / 1M: $0.60

Senova Canvas 1

Images

Makes and edits images from a text description: illustrations, mockups, icons and photos for slides.

Text to image
Image editing

Up to 1 MP: $0.01
Up to 2 MP: $0.02

Compare the language models

Model	Best at	Context (hosted)	Context (app today)	Max output	Speed	Vision	Tools	Thinking
Suite 1	Everyday default; code, writing, images in	128K	32K	32K	Fast	Yes	Yes	Yes
Symphony 1	Hardest problems, careful reasoning	128K	32K	32K	Moderate	No	Yes	Yes
Fugue 1	Coding agents, long tool use	128K	32K	32K	Fast	No	Yes	Yes
Prelude 1	Quick answers, high volume	128K	32K	32K	Fastest	No	Yes	Low / high
Étude 1	Simple edits, short tasks	128K	32K	32K	Fast	No	Yes	Yes

API pricing

Prices are per million tokens. Cached input applies when a request starts with the same text as a recent request, such as a long system prompt or the files an agent already read. Thinking tokens are billed as output.

Model	Input	Cached input	Output	Batch (50% off)	Example: 1,000 chats*
Suite 1	$0.25	$0.05	$1.50	$0.125 / $0.75	$1.80
Symphony 1	$0.75	$0.15	$3.75	$0.375 / $1.875	$4.88
Fugue 1	$0.20	$0.05	$0.90	$0.10 / $0.45	$1.23
Prelude 1	$0.10	$0.03	$0.50	$0.05 / $0.25	$0.65
Étude 1	$0.12	$0.03	$0.60	$0.06 / $0.30	$0.78
Canvas 1	$0.01 / image up to 1 MP		$0.02 up to 2 MP	$0.005 / $0.01	$10.00 (1,000 images)

* One chat = 3,000 input tokens and 700 output tokens, no caching. A typical coding-agent task reads far more than it writes, so cached input matters most there: a 25-step task on Fugue 1 with 300,000 input tokens (90% cached) and 12,000 output tokens costs about $0.03.

Speed labels are relative. On the hosted API we expect the fastest models to stream well over 100 tokens per second per request; we will publish measured figures before launch. In the desktop app, speed depends on your computer.

Voice API pricing

Bring Senova's voices to your own app with an API key: text to speech with Aria and speech to text with Notation, OpenAI-compatible, paid from the same prepaid credit. See the voice API docs.

Model	Does	Price	Example
Aria 1	Text to speech, 28 English voices	$6 per 1M characters	$0.006 for 1,000 characters
Aria 2	Text to speech, 23 languages	$10 per 1M characters	$0.01 for 1,000 characters
Notation 1	Speech to text	$0.003 per minute, billed per second	$0.18 for an hour
Notation 2	Speech to text, more accurate, 30 languages	$0.006 per minute, billed per second	$0.36 for an hour

Aria 2 and Notation 2 are switched on as they launch; GET /v1/audio/voices lists what your key can call today.

Which one should I use?

If you want to	Use	Why
Get started, or you are not sure	Suite 1	Good at almost everything, reads images, quick.
Run an agent that edits a project	Fugue 1	Holds up over long chains of tool calls; cheap input.
Solve something hard once	Symphony 1	Spends longer thinking and gets more right first time.
Handle lots of short requests	Prelude 1	Lowest price and fastest replies.
Make a small, obvious edit	Étude 1	Light and quick for simple changes.
Make a picture	Canvas 1	Text to image and image editing.

Senova models are built on open-source models used under their licences; see Open-source licenses in the Senova app under Settings › About. Prices in US dollars, excluding taxes. Proposed prices dated 27 October 2026.