Best LLM for Summarization in 2026
For summarization, Gemini 3.5 Flash Lite is our pick: $0.27/M tokens on a Document summarization workload, 162 tokens/sec, 1M context.
Summarization is a long-input, short-output workload — you pay mostly for the input tokens, so a model's input price and context window matter more here than raw output quality.
What is the best LLM for summarization?
Gemini 3.5 Flash Lite, from Google, is the best fit for summarization at $0.27 per million task tokens on a Document summarization workload, measured at 162 tokens/sec, with a 1M-token context window. No cheaper value pick beats it for this task.
Evidence
Ranked — top 8 eligible models
"Fit" is a requirements match, not a quality benchmark — it combines price, measured speed, context window, and (where we have run it) graded accuracy on this task. Formula below.
| # | Model | Provider | Fit | Evidence | Task price/M | Tokens/sec | Context | Scored on |
|---|---|---|---|---|---|---|---|---|
| 1 | Gemini 3.5 Flash Lite | 64 | — | $0.27 | 162 | 1M | price, context, speed | |
| 2 | Gemini 3.1 Pro | 61 | — | $2.16 | 55 | 2M | price, context, speed | |
| 3 | GLM-5.2 | Z.ai | 57 | — | $1.45 | — | 1M | price, context |
| 4 | Grok 4.3 | xAI | 53 | — | $1.27 | 98 | 1M | price, context, speed |
| 5 | Amazon Nova Lite | Amazon | 52 | — | $0.06 | 108 | 300K | price, context, speed |
| 6 | Gemini 3.6 Flash | 51 | — | $1.62 | 114 | 1M | price, context, speed | |
| 7 | Grok-4.20 | xAI | 49 | — | $2.06 | 104 | 1M | price, context, speed |
| 8 | Grok-4.20 Reasoning | xAI | 49 | — | $2.06 | 52 | 1M | price, context, speed |
What this costs you
At 10,000 document summarization calls/month:
| Model | Task price/M | Est. monthly cost |
|---|---|---|
| Gemini 3.5 Flash Lite | $0.27 | $137.00 |
| Gemini 3.1 Pro | $2.16 | $1096.00 |
| GLM-5.2 | $1.45 | $735.20 |
How we ranked this
Weights: evidence 0%, price 40%, speed 10%, context 50%.
Requirements: ≥128K context. 32 models eligible.
Price and context sub-scores are min-max normalised (log-scaled) within this task's eligible set only. Speed uses measured tokens/sec only — estimated rows are excluded. A model missing a measurement is never scored as zero: its weight is redistributed across the components we do have, and "Scored on" in the table above shows exactly which ones.
Prices verified 2026-08-08.
Related
FAQ
Why does price dominate this ranking?
Summarization workloads are input-heavy by nature — with a 50K-token document and an 800-token summary, input tokens are over 98% of the bill.
Does a cheaper model summarize worse?
We have not graded this task directly — run your own documents through the top picks below and compare before committing to one at volume.
Should I chunk long documents instead of using a big context window?
Chunking adds complexity and can lose cross-section context; a single large-context call is simpler when the model supports it and the price difference is small.