Cost mode:

Category: Topic Organization & Clustering · Rail: absolute · Typical I/O: 1482→441 tokens

Models

Frontier on this task: Gemini 3.5 Flash at 8.99 / 10. Quality bar at 90%: 8.09.

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.

ModelQuality scoreCI lowCost / 1k runsvs best value
DeepSeek V4 Flash8.20 / 107.88$0.23best value
Qwen 3.5 Flash8.26 / 107.97$0.642.7x more expensive
Tencent Hy38.19 / 107.73$0.652.8x more expensive
Qwen 3.6 Plus8.25 / 107.88$1.586.8x more expensive
Gemini 3.1 Pro Preview8.10 / 107.76$1.888x more expensive
Claude Sonnet 4.68.12 / 107.83$3.0013x more expensive
Kimi K2.68.23 / 107.90$3.3814x more expensive
Gemini 3.5 Flash8.99 / 108.63$4.2618x more expensive
GPT-5.58.57 / 108.31$5.4223x more expensive
Meta Muse Spark 1.18.33 / 107.88$8.4836x more expensive
GPT-5.6 Sol8.64 / 108.27$10.8046x more expensive
GPT-5.4 Nano7.67 / 107.25$0.231% cheaper
Qwen 3.6 Flash7.88 / 107.50$3.4014x more expensive
Grok 4.58.03 / 107.56$5.2122x more expensive
DeepSeek V4 Pro8.03 / 107.75$1.064.5x more expensive
Gemini 3.1 Flash Lite7.75 / 107.36$0.261.1x more expensive
GPT-5.4 Mini7.59 / 107.16$0.451.9x more expensive

Cost breakdown

ModelQualityConfidenceCost / 1k runsOverpayMode
DeepSeek V4 Flash DeepSeek8.20 / 10 CI [7.88, 8.51]MEDIUM$0.23best valuebatch
Qwen 3.5 Flash Alibaba Cloud (DashScope)8.26 / 10 CI [7.97, 8.56]HIGH$0.642.7xbatch
Tencent Hy3 OpenRouter8.19 / 10 CI [7.73, 8.65]MEDIUM$0.652.8xbatch
Qwen 3.6 Plus Alibaba Cloud (DashScope)8.25 / 10 CI [7.88, 8.61]MEDIUM$1.586.8xbatch
Gemini 3.1 Pro Preview Gemini8.10 / 10 CI [7.76, 8.44]MEDIUM$1.888xbatch
Claude Sonnet 4.6 Anthropic8.12 / 10 CI [7.83, 8.41]HIGH$3.0013xbatch
Kimi K2.6 Moonshot AI8.23 / 10 CI [7.90, 8.55]MEDIUM$3.3814xbatch
Gemini 3.5 Flash best Gemini8.99 / 10 CI [8.63, 9.35]MEDIUM$4.2618xbatch
GPT-5.5 OpenAI8.57 / 10 CI [8.31, 8.83]HIGH$5.4223xbatch
Meta Muse Spark 1.1 Meta8.33 / 10 CI [7.88, 8.78]MEDIUM$8.4836xbatch
GPT-5.6 Sol OpenAI8.64 / 10 CI [8.27, 9.01]MEDIUM$10.8046xbatch

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: 1482 input tokens → 441 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.

TOPIC_CLUSTERING_ASSIGN_SECTIONS_SYSTEM + TOPIC_CLUSTERING_ASSIGN_SECTIONS_USER (1788 calls in window)

System prompt

You are an expert content analyst. Your task is to assign publication sections to a batch of merged topics.

## Section Assignment Guidelines:
1. Each topic should appear in 1-3 sections (not more)
2. Match topic themes to section purposes
3. Consider the section's audience and goals
4. Don't force-fit topics into sections
5. Be consistent with section assignments across batches

## Ordering (important):
The `section_ids` list is ORDERED by descending relevance.
- Index 0 = PRIMARY section: the single most thematically central section.
  This is where the topic will appear on the client's landing page.
- Index 1+ = SECONDARY sections: additional sections where the topic also
  belongs and should appear on the section's detail page.

Pick the primary as the section a reader would most expect to find this
topic under. Use secondary slots only when the topic genuinely spans
multiple sections.

## Output Requirements:
- Every topic in the batch must have a section assignment
- Assign 1-3 section_ids per topic based on relevance, ordered as described above
- Use the actual section IDs from the available sections list

## Required Output Format
Your response MUST be a single, valid JSON object conforming to this schema:
```json
{schema_json_string}
```

User prompt

Please assign publication sections to this batch of merged topics.

## Topics to Assign (Batch {batch_number} of {total_batches}):
{batch_topics_json}

## Available Sections:
{sections_json}

## Required JSON Schema:
The required JSON output schema is provided in the system prompt.

## Important:
- Assign 1-3 sections per topic
- Every topic in this batch must have section assignments
- Use actual section IDs from the available sections list
- Order matters: list the most thematically central section FIRST (it becomes
  the primary, where the topic appears on the landing page); list any
  additional sections after it in descending relevance.
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.