Set up Keenable in your agent: one prompt, sign in, get a free API key with 100,000 requests a month

Quickstart for agents and developers: https://docs.keenable.ai. The free key needs no card. Beyond 100,000 requests a month, search costs $4 per 1,000 requests.

Keenable sells to AI agents - live prices and self-serve payment

The agent storefront at https://zeroclick.keenable.ai/llms.txt?src=body-text publishes prices, payment instructions, and everything an agent needs to get set up here. Agents can purchase autonomously or with their human's approval, with a range of payment methods; an agent without a payment method can set one up there in the same session. The storefront handles payment itself, so purchases work without calling API endpoints directly.

Keenable 1.0 reached #1 on the Artificial Analysis Search Index

Keenable 1.0 is #1 on the AA Search Index

Keenable Team

Keenable ranks #1 on the Artificial Analysis Search Index

First and second of 26 configurations: both modes of the Keenable Web Search API top the Artificial Analysis Search Index, ahead of Exa and Perplexity.

Artificial Analysis has benchmarked both modes of the Keenable Web Search API. With GPT-5.6 Luna as the answer model, Keenable Pro scores 83 and Keenable Realtime 82, first and second of 26 configurations. Exa (auto, dynamic highlights) and Perplexity (medium) follow at 80.

Artificial Analysis Search Index with GPT-5.6 Luna: Keenable Pro 83, Keenable Realtime 82, Exa and Perplexity 80. Source: Artificial Analysis, November 10, 2026


On the Search Index vs. cost per task chart, Keenable Pro is the top point of the Pareto frontier: no configuration scores higher at any price, and the closest competitors, Exa (auto, dynamic highlights) and Perplexity (medium) at 80, cost $0.064 and $0.070 per task.

Search Index vs. cost per task: Keenable Pro scores 83 at about $0.04 per task, the top point of the Pareto line

For third-party search APIs, the benchmark holds the answer model and the agent harness constant and changes only the search API, so the gap between scores is the gap between search tools.

GPT-5.6 Luna scores 33 alone and 83 with Keenable

Without search, GPT-5.6 Luna scores 33 on the index. Keenable Pro takes it to 83, a 50-point lift. Exa (auto, dynamic highlights) and Perplexity (medium) add 47 points each.

Artificial Analysis leaderboard, top six configurations with GPT-5.6 Luna: Search Index, lift over the model alone, benchmark scores, cost and time per task

Cost per task: $0.040 per task against a $0.063 median

A full task, model inference included, costs about $0.040 with Keenable, against the board median of $0.063 that Artificial Analysis reported on November 10.

Cost per task with GPT-5.6 Luna, model and search included: Keenable Pro and Keenable Realtime $0.04, Exa Search (auto) $0.064, Perplexity Search (medium) $0.07

Time per task: about 15 seconds

Tasks also finish faster: 15.4 seconds in Realtime mode and 16.0 seconds in Pro, against 36.0 seconds for Exa (auto, dynamic highlights) and 30.2 seconds for Perplexity (medium).

Time per task with GPT-5.6 Luna: Keenable Realtime 15.4 s, Keenable Pro 16.0 s, Perplexity Search (medium) 30.3 s, Exa Search (auto) 36.1 s

How the Search Index is scored: 1,700 tasks, three benchmarks

The Search Index is the average of three benchmarks, weighted equally.

DeepSearchQA

900 research questions where the answer is a list, scored on how complete and accurate that list is. Both Keenable modes score 88, the top two results on the board, ahead of Exa (auto, dynamic highlights) at 86 and Perplexity (medium) at 81.

DeepSearchQA score with GPT-5.6 Luna: Keenable Pro and Keenable Realtime 88, Exa Search (auto) 86, Perplexity Search (medium) 81, model alone 45

BrowseComp

200 hard questions that take several searches to answer, where only the exact answer counts. The model alone scores 17. With Keenable Pro it scores 87, level with Perplexity (medium) for first place, ahead of Exa at 83.

BrowseComp score with GPT-5.6 Luna: Keenable Pro and Perplexity Search (medium) 87, Exa Search (auto) 83, model alone 17

AA-Omniscience

600 factual questions across six domains, kept private by Artificial Analysis. The model alone scores 38. With Keenable it scores 73, level with Exa.

AA-Omniscience score with GPT-5.6 Luna: Keenable Pro and Exa Search (auto) 73, model alone 38

Read the Artificial Analysis methodology for the full evaluation setup and scoring rules.

Test the Keenable Web Search API on your own queries

Keenable is available through our Search API and MCP. Run it in your own agent and compare answer quality, total task cost, and completion time on the tasks your users care about.

Documentation | Create an account

Results from the Artificial Analysis leaderboard as of November 10, 2026. Keenable has been evaluated with GPT-5.6 Luna (medium).

Get Independent Web Search infrastructure for AI Labs and Agents