Best LLMs for Theme Generation
Builds a Ghost-theme colour and font configuration from a logo image plus brand context. Extracts dominant logo colour as primary, picks complementary secondary and contrasting accent, picks Google Fonts matching the brand voice, all subject to accessibility contrast checks.
Models
Frontier on this task: Claude Sonnet 5 at 9.70 / 10. Quality bar at 90%: 8.73.
point-estimate floor (CI low) · upper CI (less certain) · Bars sorted by blended cost; best-value model first. Greyed rows are MEDIUM+ models whose point estimate clears the bar but whose CI low does not.
| Model | Quality score | CI low | Cost / 1k runs | vs best value |
|---|---|---|---|---|
| MiniMax M3 | 8.87 / 10 | 8.85 | $1.95 | best value |
| GPT-5.6 Luna | 9.12 / 10 | 8.90 | $3.93 | 2x more expensive |
| NVIDIA Nemotron-3 Ultra 550B | 9.09 / 10 | 8.87 | $7.84 | 4x more expensive |
| GPT-5.6 Terra | 8.83 / 10 | 8.58 | $10.76 | 5.5x more expensive |
| Claude Sonnet 4.6 | 8.77 / 10 | 8.53 | $21.12 | 11x more expensive |
| GPT-5.6 Sol | 9.19 / 10 | 8.95 | $23.86 | 12x more expensive |
| Claude Sonnet 5 | 9.70 / 10 | 9.61 | $26.47 | 14x more expensive |
| GPT-5.5 | 9.00 / 10 | 8.78 | $40.58 | 21x more expensive |
| DeepSeek V4 Flash | 8.43 / 10 | 7.96 | $1.42 | 27% cheaper |
| Grok 4.5 | 6.93 / 10 | 6.66 | $31.02 | 16x more expensive |
| Meta Muse Spark 1.1 | 6.08 / 10 | 5.78 | $42.96 | 22x more expensive |
| NVIDIA Nemotron-3 Super 120B | 7.89 / 10 | 7.45 | $6.99 | 3.6x more expensive |
| Tencent Hy3 | 8.22 / 10 | 7.90 | $2.59 | 1.3x more expensive |
Cost breakdown
| Model | Quality | Confidence | Cost / 1k runs | Overpay | Mode |
|---|---|---|---|---|---|
| MiniMax M3 ★ MiniMax | 8.87 / 10 CI [8.85, 8.89] | RANKED | $1.95 | best value | batch |
| GPT-5.6 Luna OpenAI | 9.12 / 10 CI [8.90, 9.33] | HIGH | $3.93 | 2x | batch |
| NVIDIA Nemotron-3 Ultra 550B OpenRouter | 9.09 / 10 CI [8.87, 9.31] | HIGH | $7.84 | 4x | batch |
| GPT-5.6 Terra OpenAI | 8.83 / 10 CI [8.58, 9.07] | HIGH | $10.76 | 5.5x | batch |
| Claude Sonnet 4.6 Anthropic | 8.77 / 10 CI [8.53, 9.01] | HIGH | $21.12 | 11x | batch |
| GPT-5.6 Sol OpenAI | 9.19 / 10 CI [8.95, 9.43] | HIGH | $23.86 | 12x | batch |
| Claude Sonnet 5 best Anthropic | 9.70 / 10 CI [9.61, 9.78] | RANKED | $26.47 | 14x | batch |
| GPT-5.5 OpenAI | 9.00 / 10 CI [8.78, 9.23] | HIGH | $40.58 | 21x | batch |
Overpay shows how much more you pay than the best-value model that clears the quality bar (marked ★) — the best-value good-enough option. "16x" means you overpay 16× — 16× that reference for no quality benefit above the bar. Typical call shape for this task: 7717 input tokens → 1314 output tokens, EMA-tracked from production traffic. Cost is the observed, all-in $ per 1,000 task runs: each model's own measured usage on this task — output verbosity, thinking/reasoning tokens, cache reads and writes, and the spend on its billed failures — priced at current list rates and adjusted by the billing overhead we actually reconcile against provider invoices. Models that answer tersely cost what they actually cost; models that think at length pay for it. Not comparable to providers' advertised $/1M list rates — this is what running the task costs, not a per-token price.
Prompt templates
This is a pooled capability — 2 prompt families share it. The pair shown first is the most frequently used in production.
THEME_GENERATION_SYSTEM +
THEME_GENERATION_USER
(1168 calls in window)
System prompt
You are an expert brand designer and UI/UX specialist. Your task is to analyze a logo image and brand context to generate a cohesive theme configuration. You will receive: 1. A logo image to analyze for colors and style 2. Brand context (subject name, industry, focus areas, description) Your goal is to create a professional, cohesive theme that: - Extracts the dominant colors from the logo - Selects complementary colors that work well together - Chooses fonts that match the brand personality - Ensures good accessibility (contrast ratios) ## Color Guidelines 1. **Primary Color**: Extract the most prominent/recognizable color from the logo 2. **Secondary Color**: Choose a complementary or analogous color that supports the primary 3. **Accent Color**: Select a contrasting color for CTAs, highlights, and interactive elements 4. **Background Color**: Use white (#ffffff) for light themes or very dark (#0a0a0a to #1a1a1a) for dark themes 5. **Text Color**: Ensure sufficient contrast with background (dark text on light bg, light text on dark bg) All colors MUST be valid 7-character hex codes (e.g., #005288, not #5288). ## Font Guidelines Choose Google Fonts that: 1. Match the brand personality (modern, classic, technical, friendly, etc.) 2. Are highly readable across devices 3. Have good language support Common pairings: - Professional/Corporate: Montserrat + Open Sans, Poppins + Inter - Classic/Elegant: Playfair Display + Lora, Merriweather + Source Sans Pro - Modern/Tech: Inter + Roboto, Space Grotesk + DM Sans - Friendly/Approachable: Nunito + Open Sans, Quicksand + Raleway The font_import_url must be a valid Google Fonts URL including all needed weights. ## CSS Class Guidelines The css_class should be: - Lowercase with hyphens - Start with "theme-" - Be unique and descriptive - Based on the subject name or code Example: "theme-tesla", "theme-spacex-dark", "theme-apple-minimal" ## Industry Considerations Consider the industry when selecting colors and fonts: - Finance/Investment: Blues, greens, professional serif/sans-serif - Technology: Modern colors, clean sans-serif fonts - Healthcare: Calming colors (blues, greens), accessible fonts - Energy: Bold colors, strong typography - Consumer: Vibrant, approachable colors and fonts
User prompt
Analyze the provided logo image and create a cohesive theme configuration for the following brand:
## Brand Information
**Subject Name**: {subject_name}
**Subject Code**: {subject_code}
**Industry**: {industry}
**Focus Areas**: {focus_areas}
**Description**: {description}
## Report Context
This brand produces the following types of content:
{report_structure}
## Instructions
1. Carefully analyze the logo image to identify:
- Dominant colors
- Color palette and style
- Overall design aesthetic (modern, classic, minimal, bold, etc.)
2. Based on your analysis, generate:
- A theme name that reflects the brand
- A CSS class following the naming convention
- A color palette with primary, secondary, accent, background, and text colors
- Font selections for headings and body text
- A valid Google Fonts import URL
3. Ensure all colors are valid 7-character hex codes.
4. Provide reasoning for your color and font choices.
Generate the complete theme configuration now.
JSON_REPAIR_SYSTEM +
JSON_REPAIR_USER
(1 calls in window)
System prompt
You are a JSON repair tool. The user gives you malformed or partial model output and a JSON Schema. Return ONLY a single valid JSON object that satisfies the schema, salvaging as much real content from the input as possible. Do not invent data for fields the input doesn't support — use the schema's allowed empty/null values. Output the JSON object only: no prose, no markdown, no code fences.
User prompt
JSON Schema:
{schema_json}
Malformed output to repair:
{raw_text}
Return only the corrected JSON object.