Document Summarization: The Right Question Isn't "Which Model"
The Compare Prices tool is the fastest way to put a shortlist of LLMs in a single grid — input cost, output cost, context window, and quality score in stacked columns you can scan vertically. Provider dropdowns let you mix models across Anthropic, OpenAI, Google, Meta, DeepSeek, Mistral, and xAI without leaving the page. For Document Summarization the picking decision usually defaults to "use the model my last project used" — which is roughly the worst possible heuristic in 2026, because the price-quality frontier has shifted three times in the past year. The right question is "which combination of price tier, context length, and quality score fits Document Summarization traffic patterns?" The Compare Prices grid is built for that question. This guide walks through three picks for Document Summarization and shows how to grid them. For the underlying math, see tokens-to-dollars conversion; for routing strategy see multi-model routing with quality scores.
The Workload Profile of Document Summarization
Document Summarization workloads have a few distinguishing characteristics: long input (the document), short structured output (the summary), no chain-of-thought; quality has to capture the document's main points without hallucination. That profile tells you which columns of the Compare Prices grid matter most. Input cost first (documents are large), context window second (must fit the document), quality third (summaries must be accurate). It also tells you which tier you should be in. For most Document Summarization traffic, the Balanced tier is the production default — quality high enough to ship to real users at scale, price low enough to make the unit economics work.
Top Pick: Claude Haiku 4.5
For Document Summarization, Claude Haiku 4.5 is the default candidate. Pricing: $1.00 input / $5.00 output per 1M tokens. Context: 200K. Quality score: 65. Tier: fast. Why it wins: highest Value column ranking for input-heavy summarization workloads at production volume. Add it to the Compare Prices grid and the Value column makes the case visually (65 quality per dollar of input cost). Where it loses: on very long documents (200K+ tokens) where Gemini's 1M context is the differentiator.
Runner-Ups and When to Pick Them
**GPT-5 mini** ($0.300 / $2.40, Q70) — pick this when you want the production-default balance of quality (70) and price ($0.300 input). **Gemini 2.5 Flash** ($0.300 / $2.50, Q68) — pick this when traffic volume is high enough that the per-token savings dominate ($0.300 input is hard to beat). All three live in the same Compare Prices view so the comparison is one screen, not three browser tabs. For workload-specific cost modeling, run your token volume through /tools/api-cost-estimator.
Compare-Prices Workflow for Document Summarization
Workflow: (1) open /tools/compare-prices, (2) check the three picks across their provider dropdowns, (3) sort the resulting grid by Value column, (4) shortlist the top 1-2, (5) run an A/B against your real Document Summarization traffic for a week. The shortlisting step is where 90% of the time savings happen — the grid eliminates obvious losers (low quality, wrong context, output-cost surprises) in seconds. The grid pulls prices live from OpenRouter and quality from a blended Arena AI + Artificial Analysis pipeline — both refresh on a 60-minute incremental cache, so the comparison reflects current rates not a baked-in snapshot. Run the comparison live at /tools/compare-prices, then bookmark the URL for next month's price audit.