AiGanakCheapest AI for summarising documents and calls, by model and language
Summarise documents or calls: what a typical job costs on every current OpenAI, Anthropic and Google model, in English, Hindi, Tamil and German. A summary must keep what matters and drop the rest without inventing anything. Mid-class models are the usual choice.
Summarise documents or calls: a typical job is 4,700 tokens per summary. At list prices checked 9 November 2026, the lowest-cost mid-class model is Gemini 3.8 Flash in English ($5.00 per 1,000 summaries) and Gemini 3.8 Flash in Hindi ($5.86 per 1,000 summaries). Costs shown for English, Hindi, Tamil and German on every current OpenAI, Anthropic and Google model.
The pick, by language
Mid class is the smallest model class that normally handles this job. The pick is the lowest-cost current model of that class or above.
| Language | Lowest-cost model | Per 1,000 summaries | Per month at 2,000 summaries |
|---|---|---|---|
| English | Gemini 3.8 Flash Google | $5.00 | $10 |
| Hindi | Gemini 3.8 Flash Google | $5.86 | $12 |
| Tamil | Gemini 3.8 Flash Google | $6.71 | $13 |
| German | Gemini 3.8 Flash Google | $6.37 | $13 |
Cost per 1,000 summaries
Typical job: 300 tokens of instructions, 4,000 read and 400 written per summary, counted in English tokens on the reference model family and converted for each model family and language with the measured token tax (4 November 2026). Standard list prices, no caching, no batch discount.
| Model | English | Hindi | Tamil | German |
|---|---|---|---|---|
| GPT-6 Luna OpenAI · Small | $0.630 | $0.887 | $1.18 | $0.778 |
| Claude Haiku 5.5 Anthropic · Small | $0.924 | $2.05 | $2.87 | $1.80 |
| Gemini 3.5 Flash-Lite Google · Small | $2.42 | $2.85 | $3.26 | $3.09 |
| Gemini 3.8 Flash Google · Mid | $5.00 | $5.86 | $6.71 | $6.37 |
| GPT-6.1 Terra OpenAI · Mid | $6.30 | $8.87 | $11.78 | $7.78 |
| GPT-6.1 Sol OpenAI · Mid | $12.60 | $17.73 | $23.56 | $15.56 |
| Gemini 4 Argon Google · Flagship | $13.33 | $16.85 | $21.59 | $16.77 |
| Gemini 3.1 Pro (preview) Google · Flagship · older or preview | $14.18 | $16.63 | $19.05 | $18.07 |
| Claude Sonnet 5.5 Anthropic · Mid | $18.49 | $41.05 | $57.49 | $35.97 |
| Claude Opus 5.5 Anthropic · Flagship | $36.98 | $82.11 | $114.98 | $71.93 |
| GPT-6 Astra OpenAI · Flagship | $63.00 | $88.65 | $117.78 | $77.78 |
| Claude Fable 5.1 Anthropic · Flagship | $92.45 | $205.27 | $287.45 | $179.84 |
Announced price changes are not included here: Gemini 4 Argon from 1 December 2026; Gemini 3.8 Flash from 1 January 2027. AiGanak Check applies them. The size of a job is an estimate; your own prompts and replies decide your bill. Quality on your task decides whether a cheaper model is usable.
Summarise: questions
Can't find it? Press ⌘K and ask.
Which AI model is cheapest for summarising documents and calls?
For a typical job of 300 instruction tokens, 4,000 tokens read and 400 tokens written per summary, the lowest-cost mid-class model at list prices checked 9 November 2026 is Gemini 3.8 Flash in English at $5.00 per 1,000 summaries. Smaller models cost less but may not reach the quality this job needs.
Does summarising documents and calls cost more in Hindi or Tamil?
Usually yes, because the same text takes more tokens. The lowest-cost mid-class model is Gemini 3.8 Flash in Hindi at $5.86 per 1,000 summaries and Gemini 3.8 Flash in Tamil at $6.71 per 1,000 summaries, against $5.00 in English. Instructions stay in English in these figures.
How is the cost per summary worked out?
Tokens read and written per summary are multiplied by each model's list price per million tokens, using the measured token counts of that model family for each language (AiGanak token tax index, 4 November 2026). Caching, batch discounts and retries are not included; AiGanak Check lets you turn them on.
Price another job
Support replies · Extract fields · Classify messages · Translate · Research reports · Coding help · Document Q&A · Something else
Your real summaries, priced on every model
The tables use a typical job. Your bill depends on your prompts, reply lengths and mix of languages. Send one month of usage and a sample of requests, and we price your actual traffic on every model and show the changes that are safe to make.
Delivered in two working days. If the savings identified come to less than USD 149 over three months, we refund what you paid.
Get an email when a price change affects these costs
We check OpenAI, Anthropic and Google pricing every week and email you the old price, the new price and the date.