Cost Calculator
Compare 32 AI models for meeting notes. 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.
Transcripts are long and low-density (an hour of conversation is a lot of tokens carrying comparatively little information) while the notes that come back are short. That ratio makes this a strong fit for a fast-tier model plus the batch API: notes rarely need to exist within seconds of the meeting ending, and batch discounts apply to the whole request.
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 8,000 input / 2,000 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.
Transcripts are long and low-density (an hour of conversation is a lot of tokens carrying comparatively little information) while the notes that come back are short. That ratio makes this a strong fit for a fast-tier model plus the batch API: notes rarely need to exist within seconds of the meeting ending, and batch discounts apply to the whole request. Across the 32 models we track, a typical call uses about 8,000 input and 2,000 output tokens.
GPT 6 Luna from GPT is the lowest-cost model we track for meeting notes, 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 meeting notes, 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.