HomeBenchmarksProcurement › Purchase Requisition
Procurement

How much does an AI agent cost to run Purchase Requisition?

Token cost benchmark for an autonomous Purchase Requisition agent, across 13 models. Prices as of 14 Jun 2026.

An agent for Purchase Requisition on the clean path costs about $0.0277 to $1.93 per outcome depending on the model, around 25x the cost of a single chat message. At 10,000 outcomes a month that is roughly $277 to $19,270.
Estimate your own numbers →

Cost per outcome by model

Model$/1M in$/1M outCost / outcomeCost / month*
GPT-4o mini$0.15$0.60$0.0277$277
Llama 4 Maverick$0.27$0.85$0.0481$481
Gemini 2.5 Flash$0.30$2.50$0.0656$656
GPT-4.1 mini$0.40$1.60$0.0740$740
DeepSeek V4$0.44$0.87$0.0744$744
Claude Haiku 4.5$1.00$5.00$0.193$1,927
Gemini 2.5 Pro$1.25$10.00$0.270$2,701
Mistral Large 3$2.00$6.00$0.354$3,542
GPT-4.1$2.00$8.00$0.370$3,698
GPT-4o$2.50$10.00$0.462$4,622
Claude Sonnet 4.6$3.00$15.00$0.578$5,781
Claude Opus 4.8$5.00$25.00$0.964$9,635
Claude Fable 5$10.00$50.00$1.93$19,270

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

What this agent does

The clean-path steps this benchmark prices:

  1. Validate & Enrich
  2. Catalog item?
  3. Within budget?
  4. Approve requisition?
  5. Raise Purchase Order
  6. Dispatch to Vendor
  7. Goods received?
  8. Goods Receipt (GRN)
  9. 3-way match OK?
  10. Match & Close

What drives the cost

This path runs 10 steps: 3 tool calls, 2 reasoning steps, 5 decision points and 0 human checkpoints. Tool steps make two model calls each, and the agent re-reads its growing context on every call. That compounding is why one Purchase Requisition outcome costs about 25x a single chat message ($0.578 on Claude Sonnet 4.6), not the price of one message.

Why these numbers matter.

Frequently asked questions

How much does an AI agent cost to run Purchase Requisition?

On the clean path with default assumptions, an agent for Purchase Requisition costs about $0.0277 to $1.93 per outcome depending on the model, or roughly $277 to $19,270 per month at 10,000 outcomes. The cheapest model here is GPT-4o mini at $0.0277; the most expensive is Claude Fable 5 at $1.93.

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 Purchase Requisition that adds up to about 25x the cost of a single chat message.

Which model is cheapest for Purchase Requisition?

Across the 13 models benchmarked, GPT-4o mini is cheapest at $0.0277 per outcome and Claude Fable 5 is the most expensive at $1.93. 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 Purchase Requisition?

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.

More Procurement benchmarks

Open Purchase Requisition in the live estimator →