HomeBenchmarksHR › Recruiting & Screening
HR

How much does an AI agent cost to run Recruiting & Screening?

Token cost benchmark for an autonomous Recruiting & Screening agent, across 26 models. Prices as of 26 Jul 2026.

An agent for Recruiting & Screening on the clean path costs about $0.0216 to $1.50 per outcome depending on the model, around 19x the cost of a single chat message. At 10,000 outcomes a month that is roughly $216 to $15,000.
Estimate your own numbers →

Cost per outcome by model

Model$/1M in$/1M outCost / outcomeCost / month*
GPT-4o mini$0.15$0.60$0.0216$216
Llama 4 Maverick$0.27$0.85$0.0375$375
Gemini 2.5 Flash$0.30$2.50$0.0510$510
DeepSeek V4$0.43$0.87$0.0574$574
GPT-4.1 mini$0.40$1.60$0.0576$576
Mistral Large 3$0.50$1.50$0.0690$690
Qwen3.5 397B$0.60$3.60$0.0936$936
Kimi K2.6$0.95$4.00$0.138$1,380
Claude Haiku 4.5$1.00$5.00$0.150$1,500
Grok 4.3$1.25$2.50$0.165$1,650
Qwen3.7 Max$1.25$3.75$0.172$1,725
GLM-5.2$1.40$4.40$0.194$1,944
Gemini 2.5 Pro$1.25$10.00$0.210$2,100
Mistral Medium 3.5$1.50$7.50$0.225$2,250
Gemini 3.5 Flash$1.50$9.00$0.234$2,340
GPT-4.1$2.00$8.00$0.288$2,880
Claude Sonnet 5$2.00$10.00$0.300$3,000
GPT-4o$2.50$10.00$0.360$3,600
GPT-5.4$2.50$15.00$0.390$3,900
GPT-5.6 Terra$2.50$15.00$0.390$3,900
Claude Sonnet 4.6$3.00$15.00$0.450$4,500
Kimi K3$3.00$15.00$0.450$4,500
Claude Opus 4.8$5.00$25.00$0.750$7,500
GPT-5.5$5.00$30.00$0.780$7,800
GPT-5.6 Sol$5.00$30.00$0.780$7,800
Claude Fable 5$10.00$50.00$1.50$15,000

*At 10,000 outcomes per month. Cheapest model highlighted.

What this agent does

The clean-path steps this benchmark prices:

  1. Parse Role & Criteria
  2. Source Candidates
  3. Screen & Rank
  4. Qualified pool?
  5. Borderline calls?
  6. Confidence high?
  7. Schedule Interviews

What drives the cost

This path runs 7 steps: 3 tool calls, 1 reasoning step and 3 decision points. Tool steps make two model calls each, and the agent re-reads its growing context on every call. That compounding is why one Recruiting & Screening outcome costs about 19x a single chat message ($0.450 on Claude Sonnet 4.6), not the price of one message.

Why these numbers matter.

How this benchmark is calculated

These figures are modeled estimates, not metered bills. We price a generic, representative Recruiting & Screening workflow across 26 models using the same cost engine as the live estimator, at each model’s published list price (checked 26 Jul 2026), under documented default assumptions for planning loops, tool calls, memory retrieval, sub-agents and context size. Your own process will differ, so use these as starting points, tune the assumptions in the estimator, and validate against your real usage. Illustrative estimates, not financial advice.

Frequently asked questions

How much does an AI agent cost to run Recruiting & Screening?

On the clean path with default assumptions, an agent for Recruiting & Screening costs about $0.0216 to $1.50 per outcome depending on the model, or roughly $216 to $15,000 per month at 10,000 outcomes. The cheapest model here is GPT-4o mini at $0.0216; the most expensive is Claude Fable 5 at $1.50.

Why does an AI agent cost more than a single chatbot message?

An agent does not make one model call. It plans, calls tools, retrieves context and re-reads its growing working context on every step. For Recruiting & Screening that adds up to about 19x the cost of a single chat message.

Which model is cheapest for Recruiting & Screening?

Across the 26 models benchmarked, GPT-4o mini is cheapest at $0.0216 per outcome and Claude Fable 5 is the most expensive at $1.50. A cheaper model is not always the right choice, but it sets the floor for this workflow.

How can I reduce the cost of an agent for Recruiting & Screening?

The biggest levers are prompt caching on the base context, fewer planning loops, smaller tool results, less retrieval, and choosing a cheaper model where quality allows. You can test each lever in the live estimator.

What is this Recruiting & Screening benchmark based on?

These are modeled estimates, not metered bills. Each figure prices a generic, representative Recruiting & Screening workflow across 26 models with the same cost engine as the live estimator, at each model's published list price (checked 26 Jul 2026), under documented default assumptions for planning loops, tool calls, memory retrieval, sub-agents and context size. Your own process will differ, so treat these as starting points, tune them in the estimator, and validate against your own usage.

More HR benchmarks

Beyond cost: is it ready, and can you govern it?

Cost is one axis. Before you build, check the process is ready for AI and that you can prove you govern it. See how governed AI process animations work →

Open Recruiting & Screening in the live estimator →