PriceIndex

AI model capabilities

AI models that support web search

Find AI models with a listed built-in search option for web-connected applications. Compare 15 supporting models by input price, output price, context window and published intelligence. Find the cheapest option for a reference text workload, then check the serving API before you build.

15 supporting models3 AI providersUSD · prices per 1M tokens

Lowest reference cost

GPT-4o mini

$0.30

1M input + 250K output tokens. Tool fees and discounts excluded.

Highest published intelligence

Sonar Reasoning Pro

11.8 AA Intelligence Index

Among supporting models with a published score; not a capability-specific benchmark.

Cheapest AI models with web search

Ranked by the cost of 1 million input and 250,000 output tokens at standard rates. A different token mix can change the cheapest model. Support requires an explicitly listed catalog feature, not an inference from a model family.

GPT-4o miniOpenAI
Input /1M
$0.15
Output /1M
$0.60
Reference cost
$0.30
Context
128K
AA Intelligence
6.7
SonarPerplexity
Input /1M
$1.00
Output /1M
$1.00
Reference cost
$1.25
Context
127K
AA Intelligence
7.7
Fugu MaxSakana AI
Input /1M
$2.00
Output /1M
$6.00
Reference cost
$3.50
Context
1M
AA Intelligence
—
GPT-4oOpenAI
Input /1M
$2.50
Output /1M
$10
Reference cost
$5.00
Context
128K
AA Intelligence
8.4

15 matching models · Missing intelligence scores are shown as —.

What is built-in web search?

Built-in web search lets a supported serving API retrieve web information during a model request. This directory requires an explicitly listed web-search option; a model that can call your own search function is not automatically included. Search behavior, citations and access to current pages depend on the API.

Before choosing a model

  • Verify search availability for the exact model and serving API.
  • Check citations against the retrieved sources before relying on an answer.
  • Budget for search-call fees in addition to input and output tokens.

Estimate your actual workload

Use your request volume and prompt and response sizes to compare monthly text-token costs. Add any search, external tool or provider-specific charges separately. Standard token prices do not assume cache hits or batch discounts.

LLM token cost calculator Pricing methodology

Built-in web search FAQs

15 active models with positive input and output prices currently list web search in the PriceIndex catalog. The table lists every match. A model is included only when its tracked feature data explicitly lists this capability; missing data is not treated as support.

GPT-4o mini has the lowest estimated text-token cost in this list for 1 million input tokens and 250,000 output tokens: $0.3000. A different input/output mix can change the ranking. This excludes tool fees, caching, discounts and taxes.

No. Capability availability can differ between serving APIs and model versions. Follow a model’s API documentation link and verify the exact version, endpoint and settings before choosing it.

We use standard USD input and output token prices: input price × 1 million tokens plus output price × 250,000 tokens, divided by 1 million. The directory excludes retired models, missing prices and zero-priced entries. Published AA Intelligence Index scores are shown when available and never estimated.

Verify search availability for the exact model and serving API. Check citations against the retrieved sources before relying on an answer. Budget for search-call fees in addition to input and output tokens.

Explore more AI capabilities