Cost mode:

Category: Long-form Content Generation · Rail: absolute · Typical I/O: 738→2812 tokens

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.

ModelQuality scoreCI lowCost / 1k runsvs best value
MiniMax M39.08 / 109.05$0.90best value
NVIDIA Nemotron-3 Ultra 550B9.06 / 108.87$3.383.8x more expensive
Claude Sonnet 59.32 / 109.29$5.466.1x more expensive
Thinking Machines Inkling9.05 / 108.96$7.488.3x more expensive

Cost breakdown

ModelQualityConfidenceCost / 1k runsOverpayMode
MiniMax M3 OpenRouter9.08 / 10 CI [9.05, 9.11]RANKED$0.90best valuebatch
NVIDIA Nemotron-3 Ultra 550B OpenRouter9.06 / 10 CI [8.87, 9.24]RANKED$3.383.8xbatch
Claude Sonnet 5 best Anthropic9.32 / 10 CI [9.29, 9.35]RANKED$5.466.1xbatch
Thinking Machines Inkling OpenRouter9.05 / 10 CI [8.96, 9.14]RANKED$7.488.3xbatch

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.