Skip to content
Back

Model cardPro

One model at a glance: inputs, outputs, context and prices swap in place when you change model, a volume slider turns prices into a monthly bill, benchmark rows rank it, and Compare sets a rival beside it and ticks the stronger figure.

oxyn add model-card

Claude Sonnet 4.5

Anthropic

The balanced Claude for everyday coding, agents and analysis at scale.

  • Text
  • Image
  • PDF
  • Audio
  • Video
  • Tools
  • Reasoning
Context window
1M tokens
Max output
64K tokens
Knowledge cutoff
Jul 2025
Fits about 1,450 pages
Input per 1M
$3.00
Output per 1M
$15.00
Cached per 1M
$0.30
100M tokensEstimated $600/mo

Benchmarks

  • Claude Sonnet 4.577.2%
  • Claude Opus 4.174.5%
  • GPT-574.9%

SWE-bench Verified, real GitHub issues resolved. Sample prices and scores, not official.

Compare with
SpecClaude Sonnet 4.5GPT-5
ModalitiesText, Image, PDF, Tools, ReasoningText, Image, PDF, Audio, Tools, Reasoning
Context window1M tokens, better by 2.5x400K tokens
Max output64K tokens128K tokens, better by 2.0x
Knowledge cutoffJul 2025, better by +10 moSep 2024
Input price$3.00$1.25, better by −58%
Output price$15.00$10.00, better by −33%
Cost at 100M/mo$600$344, better by −43%
SWE-bench77.2%, better by +2.374.9%
GPQA83.4%85.7%, better by +2.3
Terminal-Bench50.0%, better by +6.243.8%

GPT-5 leads on 5 of 10, Claude Sonnet 4.5 on 4. Prices per 1M tokens; cost assumes 75% input. Sample figures, not official.

Couldn't load model details
claude-sonnet-4-5
The code is part of Oxyn Pro

The preview stays free for everyone. Pro opens the code of every Pro component, screen, agent-app template, block and kit, plus the Pro CLI.

Get Pro

Rendered from Rust at build time · goes live when visible

When to use

  • Decide whether a model fits a job: what it reads and writes, its context and prices, an estimated monthly cost at your volume, and how it scores against rivals.

When not to use

Installation

Model card is part of Oxyn Pro; the preview is free. Pro items install with the oxyn CLI once your licence is signed in; until then Pro members copy the code from this page.

Terminal
oxyn add model-card

Usage

Dioxus · rust
The code is part of Oxyn Pro

The preview is free. Pro opens the code of every Pro component, screen and template.

Get Pro

Examples

Details

Details of Claude Sonnet 4.5 at 100M tokens a month.

Claude Sonnet 4.5

Anthropic

The balanced Claude for everyday coding, agents and analysis at scale.

  • Text
  • Image
  • PDF
  • Audio
  • Video
  • Tools
  • Reasoning
Context window
1M tokens
Max output
64K tokens
Knowledge cutoff
Jul 2025
Fits about 1,450 pages
Input per 1M
$3.00
Output per 1M
$15.00
Cached per 1M
$0.30
100M tokensEstimated $600/mo

Benchmarks

  • Claude Sonnet 4.577.2%
  • Claude Opus 4.174.5%
  • GPT-574.9%

SWE-bench Verified, real GitHub issues resolved. Sample prices and scores, not official.

Compare with
SpecClaude Sonnet 4.5GPT-5
ModalitiesText, Image, PDF, Tools, ReasoningText, Image, PDF, Audio, Tools, Reasoning
Context window1M tokens, better by 2.5x400K tokens
Max output64K tokens128K tokens, better by 2.0x
Knowledge cutoffJul 2025, better by +10 moSep 2024
Input price$3.00$1.25, better by −58%
Output price$15.00$10.00, better by −33%
Cost at 100M/mo$600$344, better by −43%
SWE-bench77.2%, better by +2.374.9%
GPQA83.4%85.7%, better by +2.3
Terminal-Bench50.0%, better by +6.243.8%

GPT-5 leads on 5 of 10, Claude Sonnet 4.5 on 4. Prices per 1M tokens; cost assumes 75% input. Sample figures, not official.

Couldn't load model details
claude-sonnet-4-5
Code Pro
The code is part of Oxyn Pro

The preview is free. Pro opens the code of every Pro component, screen and template.

Get Pro

Compare

GPT-5 against a rival with the better values checked.

GPT-5

OpenAI

OpenAI's flagship for reasoning, coding and multimodal work.

  • Text
  • Image
  • PDF
  • Audio
  • Video
  • Tools
  • Reasoning
Context window
400K tokens
Max output
128K tokens
Knowledge cutoff
Sep 2024
Fits about 550 pages
Input per 1M
$1.25
Output per 1M
$10.00
Cached per 1M
$0.12
100M tokensEstimated $344/mo

Benchmarks

  • GPT-574.9%
  • Claude Opus 4.174.5%
  • Claude Sonnet 4.577.2%

SWE-bench Verified, real GitHub issues resolved. Sample prices and scores, not official.

Compare with
SpecGPT-5Gemini 2.5 Pro
ModalitiesText, Image, PDF, Audio, Tools, ReasoningText, Image, PDF, Audio, Video, Tools, Reasoning
Context window400K tokens1M tokens, better by 2.5x
Max output128K tokens, better by 2.0x64K tokens
Knowledge cutoffSep 2024Jan 2025, better by +4 mo
Input price$1.25$1.25
Output price$10.00$10.00
Cost at 100M/mo$344$344
SWE-bench74.9%, better by +7.767.2%
GPQA85.7%86.4%, better by +0.7
Terminal-Bench43.8%, better by +18.525.3%

GPT-5 leads on 3 of 10, Gemini 2.5 Pro on 3. Prices per 1M tokens; cost assumes 75% input. Sample figures, not official.

Couldn't load model details
gpt-5
Code Pro
The code is part of Oxyn Pro

The preview is free. Pro opens the code of every Pro component, screen and template.

Get Pro

Picker pane

Shown as the side panel of a model chooser, with a Use model button (Oxyn extra).

Gemini 2.5 Pro

Google

Google's thinking model with a long context and native audio and video.

  • Text
  • Image
  • PDF
  • Audio
  • Video
  • Tools
  • Reasoning
Context window
1M tokens
Max output
64K tokens
Knowledge cutoff
Jan 2025
Fits about 1,450 pages
Input per 1M
$1.25
Output per 1M
$10.00
Cached per 1M
$0.31
100M tokensEstimated $344/mo

Benchmarks

  • Gemini 2.5 Pro67.2%
  • Claude Opus 4.174.5%
  • Claude Sonnet 4.577.2%

SWE-bench Verified, real GitHub issues resolved. Sample prices and scores, not official.

Compare with
SpecGemini 2.5 ProGPT-5
ModalitiesText, Image, PDF, Audio, Video, Tools, ReasoningText, Image, PDF, Audio, Tools, Reasoning
Context window1M tokens, better by 2.5x400K tokens
Max output64K tokens128K tokens, better by 2.0x
Knowledge cutoffJan 2025, better by +4 moSep 2024
Input price$1.25$1.25
Output price$10.00$10.00
Cost at 100M/mo$344$344
SWE-bench67.2%74.9%, better by +7.7
GPQA86.4%, better by +0.785.7%
Terminal-Bench25.3%43.8%, better by +18.5

Gemini 2.5 Pro leads on 3 of 10, GPT-5 on 3. Prices per 1M tokens; cost assumes 75% input. Sample figures, not official.

Couldn't load model details
gemini-2-5-pro
Code Pro
The code is part of Oxyn Pro

The preview is free. Pro opens the code of every Pro component, screen and template.

Get Pro

Error

Couldn't load, with Retry.

Claude Sonnet 4.5

Anthropic

The balanced Claude for everyday coding, agents and analysis at scale.

  • Text
  • Image
  • PDF
  • Audio
  • Video
  • Tools
  • Reasoning
Context window
1M tokens
Max output
64K tokens
Knowledge cutoff
Jul 2025
Fits about 1,450 pages
Input per 1M
$3.00
Output per 1M
$15.00
Cached per 1M
$0.30
100M tokensEstimated $600/mo

Benchmarks

  • Claude Sonnet 4.577.2%
  • Claude Opus 4.174.5%
  • GPT-574.9%

SWE-bench Verified, real GitHub issues resolved. Sample prices and scores, not official.

Compare with
SpecClaude Sonnet 4.5GPT-5
ModalitiesText, Image, PDF, Tools, ReasoningText, Image, PDF, Audio, Tools, Reasoning
Context window1M tokens, better by 2.5x400K tokens
Max output64K tokens128K tokens, better by 2.0x
Knowledge cutoffJul 2025, better by +10 moSep 2024
Input price$3.00$1.25, better by −58%
Output price$15.00$10.00, better by −33%
Cost at 100M/mo$600$344, better by −43%
SWE-bench77.2%, better by +2.374.9%
GPQA83.4%85.7%, better by +2.3
Terminal-Bench50.0%, better by +6.243.8%

GPT-5 leads on 5 of 10, Claude Sonnet 4.5 on 4. Prices per 1M tokens; cost assumes 75% input. Sample figures, not official.

claude-sonnet-4-5
Code Pro
The code is part of Oxyn Pro

The preview is free. Pro opens the code of every Pro component, screen and template.

Get Pro

API reference

ModelCard

PropTypeDefaultDescription
nowrequiredClockMs—Host clock.
modelusize1Starting model (0 Opus 4.1, 1 Sonnet 4.5, 2 GPT-5, 3 Gemini 2.5 Pro, 4 Grok 4).
viewString"details"`details` or `compare`.
volumeusize5Starting volume stop (0–8: 1M … 1B tokens a month).
loadingboolDefault::default()Show the skeleton.
errorboolDefault::default()Show the error state.
selectableboolDefault::default()Show the Use model button (model picker detail pane).
tabsbooltrueShow the model tabs above the card.

Read from the Rust signature and doc comments.

Keyboard interactions

KeyAction
TabModel tabs, Compare, the volume slider, benchmark switcher and rows, then Copy and Use model
←or→Model tabs and the benchmark switcher
Arrows · Page upordown · HomeorEndStep the monthly volume
Enteror↓Open the rival menu; ↑/↓ move, Enter picks, Escape closes
SpaceorEnterToggle Compare, copy the id, select the model

Accessibility

  • The card is an article labelled by the model; specs and prices are description lists.
  • Compare is a real table with headers on both axes; the stronger figure gets a tick plus the words better by, not just a colour.
  • Benchmark rows are focusable and read the full readout (score, rank, gap to the leader); the bars are decorative.
  • A modality the model lacks gets a dashed outline, a dimmer tone and the words not supported.
  • Loading sets aria-busy; errors use role alert; the polite region says what changed.
From the spec

Tabs are a tablist with arrow keys; the volume slider is a native range with a text value; compare marks the better value with text (Better) as well as the check. Every action returns the line the polite live region announces. The focus outline shows only for keyboard focus.

Motion & interaction

Switching model rolls every number in place; the card never changes size because every panel shares one grid cell. The volume slider moves the monthly estimate live. Copy model id flashes Copied for 1.2 s.

Timing

Everything on screen is derived from the host clock now (no timers in the component), so playback, tests and the GPUI view agree.

TransitionDurationEasing
Value roll on model switch180 msease-out
Panel swap (tabs, compare)160 ms crossfadeease-out
Copied flash1200 msstep

Reduced motion: streamed text and moves appear at their end state; progress still advances, without travel animation.

Responsive behaviour

  • All four panels (details, compare, loading, error) stack in the same cell, so switching never resizes the card.
  • Below 560 px the spec tiles turn into rows, the monthly figure drops below the slider and benchmark bars sit beneath their names.
  • The compare table scrolls inside its own frame rather than the page.
Edge cases (spec)

Long model names wrap to two lines in the header; the tab row scrolls horizontally under 390 px instead of wrapping onto prices. Prices use tabular figures. Compare collapses to one column of pairs under 640 px. Checked at 1440, 768 and 390 px in light and dark with no text overlap. Chrome is monochrome grey; colour is semantic only (success, warning, danger, info) plus the providers' coloured brand marks.

Notes for AI

  • Import ModelCard from oxyn_dioxus and include STATUS_INDICATOR_CSS plus the token stylesheet once.
  • A GPUI version exists: AiKitView in oxyn_gpui.
  • Props to set first: now.
  • It reads a clock (now) for live timers; pass one clock for the whole page rather than one per component.
  • Keep its states and timings as they ship; restyle it through the CSS variables rather than by hand.

Guides

Oxyn · 74 free components · 264 Pro components · 96 screens · 20 blocks · Dioxus and GPUI