Cost Calculator
Compare 32 AI models for document summarization. Prices shown at 10K calls/month with default token counts.
Summarization tasks compress long documents into concise overviews for faster reading. These tasks are input-heavy because the full source text must be included. Output stays relatively short compared to the original source document length.
The archetypal input-heavy task: the entire source document goes in, a short summary comes back. Cost is almost entirely a function of document length, and the output rate barely registers. Long documents can cross a provider's long-context threshold, where the whole request is re-priced at a multiple. Check the threshold before feeding in a hundred-page PDF as one call.
Recommendations
Best quality
Gemini 3.8 Flash
81/100 confidence
Best value
Gemini 3 Flash
83/100 confidence · $40/mo
Budget pick
GPT 5.4 Nano
67/100 confidence · $17/mo
Monthly estimates assume 10,000 input / 1,000 output tokens per call. Use the detailed page for custom calculations.
Confidence scores are a third-party benchmark snapshot from week 26 of 2026. This snapshot is 17 weeks old, so treat the scores as directional and validate against your own evals.
The archetypal input-heavy task: the entire source document goes in, a short summary comes back. Cost is almost entirely a function of document length, and the output rate barely registers. Long documents can cross a provider's long-context threshold, where the whole request is re-priced at a multiple. Check the threshold before feeding in a hundred-page PDF as one call. Across the 32 models we track, a typical call uses about 10,000 input and 1,000 output tokens.
GPT 6 Luna from GPT is the lowest-cost model we track for document summarization, at roughly $7.00 for 10,000 calls per month. It scores 53 out of 100 on this task type.
Gemini 3.8 Flash from Gemini ranks highest for document summarization, scoring 81 out of 100. Confidence scores are a third-party benchmark snapshot from week 26 of 2026. This snapshot is 17 weeks old, so treat the scores as directional and validate against your own evals.
These are estimates based on published rates. Track your real spend with the free dashboard.