ModelsatWorkWhere AI earns its keep
For your agentsGet the briefing
Best for · November 2026

Best AI model for call and meeting summaries

A call summary is mostly reading: a long transcript in, a short note out. So the bill follows the reading price. These everyday and high-volume models score in the top half of the board, listed cheapest first.

Updated Nov 12, 2026 · 8 models qualify · kept by WrenFull leaderboard

One job here means a 40-minute call transcript read; a summary and next steps written. Costs use each vendor’s list price; a product built on the model charges its own price on top. See every model and job.

  1. 1

    Claude Haiku 5.5 · Anthropic

    The pick for high-volume routine work: a twentieth of Claude Sonnet 5.5's list price, with users reporting near-perfect sorting in production, as long as each request stays short.

    $1.30 per 1,000 calls summarisedScore 73 of 100High-volume workIntelligence Index 36$0.10 read · $0.50 written per 1M tokensReads 1M tokens at once

    Caveat: The price is five times higher on any request that feeds it more than 100,000 tokens of text at once (a long document or a long back-and-forth).

  2. 2

    GPT-6 Luna · OpenAI

    OpenAI's cheapest model, at the same list price as Claude Haiku 5.5 but eight points behind it on Artificial Analysis's index (28 against 36).

    $1.30 per 1,000 calls summarisedScore 64 of 100High-volume workIntelligence Index 28$0.10 read · $0.50 written per 1M tokensReads 1M tokens at once

    Caveat: It ranks 14th largely because price is 30% of the board's score; its test result is low (28 on the index, down from 38 when Artificial Analysis rebuilt it).

  3. 3

    DeepSeek V4.1 Flash (1017) · DeepSeek

    About a seventh of Kimi K3.1 Pro's list price for 33 on Artificial Analysis's index, and now sold by Google's and Microsoft's clouds as well as DeepSeek itself.

    $3.72 per 1,000 calls summarisedScore 62 of 100High-volume workIntelligence Index 33$0.30 read · $1.20 written per 1M tokensReads 1M tokens at once

    Caveat: DeepSeek's own service is in China and charges more at peak hours: $0.15 to $0.30 in and $0.60 to $1.20 out per million tokens. Read its data terms, or buy through a US cloud.

  4. 4

    Gemini 3.8 Flash · Google

    Fast and well liked in blind votes for the money, at under half the list price of Gemini 4 Argon, but users report more made-up answers than rivals and Google doubles the price on 1 January 2027.

    $9.75 per 1,000 calls summarisedScore 65 of 100High-volume workIntelligence Index 31$0.75 read · $3.75 written per 1M tokensReads 1M tokens at once

    Caveat: $0.75 in / $3.75 out per million tokens (the unit vendors bill by) is introductory; Google's pricing page says $1.50 / $7.50 from 1 January 2027.

  5. 5

    GPT-6.1 Terra · OpenAI

    Half the list price of GPT-6.1 Sol for four points less on Artificial Analysis's index (51 against 55): the cheaper OpenAI default where the work is routine.

    $13 per 1,000 calls summarisedScore 65 of 100Everyday defaultIntelligence Index 51$1 read · $5 written per 1M tokensReads 1.05M tokens at once

    Caveat: Requests that feed it more than 272,000 tokens of text at once are billed at twice the input price and 1.5 times the output price, per OpenAI.

  6. 6

    Qwen3.8 Max · Alibaba

    Alibaba's hosted flagship scores 34 on Artificial Analysis's index, a little above the open models GLM-5.3 (32) and MiMo-V2.6-Pro (30), at about 1.4 times GLM's list price and about five times MiMo's.

    $24 per 1,000 calls summarisedScore 63 of 100Everyday defaultIntelligence Index 34$2 read · $6 written per 1M tokensReads 984K tokens at once

    Caveat: The hosted model is closed; the open version is a different model that Artificial Analysis has not scored and that needs data-centre hardware.

  7. 7

    GPT-6.1 Sol · OpenAI

    The sensible OpenAI default: 55 on Artificial Analysis's index against 57 for GPT-6 Astra, at a fifth of Astra's list price.

    $26 per 1,000 calls summarisedScore 70 of 100Everyday defaultIntelligence Index 55$2 read · $10 written per 1M tokensReads 1M tokens at once

    Caveat: Two points separate it from Astra on the index, which is within noise; test Astra only where Sol's answers fall short.

  8. 8

    Claude Sonnet 5.5 · Anthropic

    A sound everyday default: 55 on Artificial Analysis's index, four points behind Claude Opus 5.5, at half its list price.

    $26 per 1,000 calls summarisedScore 66 of 100Everyday defaultIntelligence Index 55$2 read · $10 written per 1M tokensReads 1M tokens at once

    Caveat: The saving depends on the effort setting: at the top setting Artificial Analysis's test run cost $10.02 per task, level with Opus 5.5 ($10.04).

Head to head

Questions people ask

What is the best AI model for call and meeting summaries right now?

Claude Haiku 5.5 (Anthropic) leads this list as of November 2026: The pick for high-volume routine work: a twentieth of Claude Sonnet 5.5's list price, with users reporting near-perfect sorting in production, as long as each request stays short. It costs $0.10 per million tokens it reads and $0.50 per million tokens it writes on the vendor's list price.

What is the runner-up for call and meeting summaries?

GPT-6 Luna (OpenAI): OpenAI's cheapest model, at the same list price as Claude Haiku 5.5 but eight points behind it on Artificial Analysis's index (28 against 36).

What do 1,000 calls summarised cost?

On Claude Haiku 5.5, about $1.30 at list price. That is the cheapest on this list. One job here means a 40-minute call transcript read; a summary and next steps written. A product built on a model charges its own price on top.

How is this list ranked?

Models in the everyday default and high-volume groups with a published price and a score at or above the middle of the board, ordered by the list-price cost of 1,000 call summaries, cheapest first. The score works like this: Score is 0 to 100 and computed, not typed. 40% is independent testing (Artificial Analysis, Arena, Scale, Epoch, Vals and others; each test is scaled against the best score on this board, and tests of real work, such as finished freelance projects or professional tasks, count double the exams). 30% is price: the vendor's list price for a typical mix of reading and writing, on a fixed scale from $0.05 to $60 per million tokens, so a model that costs a fifth as much gains real ground. 15% is what people report after running it, from Signals and linked threads. 15% is fit: how much text it can take in at once and where a business can get it (the products and clouds that carry it), with a small credit for open weights. A missing component drops out and the rest are reweighted. A model with no independent test yet is provisional and ranks below every measured one. Within three points is a tie. Vendor-published figures are labelled and never counted.

Other jobs

Every figure links to its source on the model profile pages. Vendor figures are labelled as vendor figures and never counted as independent tests.