Best LLMs for Newsletter Copy Generation
Generates publication-ready newsletter copy from supplied subject context, executive summary, article metadata, highlights, links, and timing configuration. Illustrative uses include producing a customer briefing, product newsletter, developer update, employee digest, industry re
Models
Frontier on this task: Claude Sonnet 5 at 9.32 / 10. Quality bar at 90%: 8.39.
point-estimate floor (CI low) · upper CI (less certain) · Bars sorted by blended cost; best-value model first.
| Model | Quality score | CI low | Cost / 1k runs | vs best value |
|---|---|---|---|---|
| MiniMax M3 | 9.08 / 10 | 9.05 | $0.90 | best value |
| NVIDIA Nemotron-3 Ultra 550B | 9.06 / 10 | 8.87 | $3.38 | 3.8x more expensive |
| Claude Sonnet 5 | 9.32 / 10 | 9.29 | $5.46 | 6.1x more expensive |
| Thinking Machines Inkling | 9.05 / 10 | 8.96 | $7.48 | 8.3x more expensive |
Cost breakdown
| Model | Quality | Confidence | Cost / 1k runs | Overpay | Mode |
|---|---|---|---|---|---|
| MiniMax M3 ★ OpenRouter | 9.08 / 10 CI [9.05, 9.11] | RANKED | $0.90 | best value | batch |
| NVIDIA Nemotron-3 Ultra 550B OpenRouter | 9.06 / 10 CI [8.87, 9.24] | RANKED | $3.38 | 3.8x | batch |
| Claude Sonnet 5 best Anthropic | 9.32 / 10 CI [9.29, 9.35] | RANKED | $5.46 | 6.1x | batch |
| Thinking Machines Inkling OpenRouter | 9.05 / 10 CI [8.96, 9.14] | RANKED | $7.48 | 8.3x | 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: 738 input tokens → 2812 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.
Evaluation rubric
Judge source fidelity, newsletter structure, reader value, voice consistency, appropriate compression, link/article accuracy, and variant fit. Penalize unsupported claims and promotional filler.
Prompt templates
The system + user template pair used for this task.
AUTO_SUBSTACK_OPENER_SYSTEM_PROMPT +
AUTO_SUBSTACK_OPENER_USER_PROMPT
(121 calls in window)
System prompt
You are a professional newsletter writer for a financial analysis and market research platform.
Your task is to write an engaging opener newsletter for Substack that announces the start of a new analysis publishing cycle. The newsletter should:
1. Build excitement about the upcoming analysis
2. Clearly communicate what the reader can expect
3. Mention the publishing timeframe so readers know when to check back
4. Include a link to the main analysis page using the literal placeholder <home_url>
5. Be concise but compelling — this is an announcement, not the full analysis
6. Use professional, engaging tone appropriate for investors and analysts
Format the newsletter in clean markdown suitable for Substack. Keep it focused — 200-400 words.
Return your response as a JSON object matching the provided schema.
## Required Output Format
Your response MUST be a single, valid JSON object conforming to this schema:
```json
{schema_json_string}
```User prompt
Write an opener newsletter announcing the start of new analysis publishing.
**Subject:** {subject_name}
**Description:** {subject_description}
**Publishing window:** New articles will be published over the next {publish_spread_hours} hours.
Use the placeholder <home_url> wherever you want to link to the main analysis page. Do NOT use any actual URLs — only the placeholder.
The required JSON output schema is provided in the system prompt.