OpenAI Web Search vs Gemini Grounding vs Perplexity Sonar: Real Grounded AI Search Cost per 100,000 Queries in 2026

The short answer: Perplexity Sonar is the only one of the three built around web search from the ground up, and it shows in the price: at 100,000 queries, Sonar's base model costs about $600 total (a $5-per-1,000-query search fee plus a small token charge), while Sonar Pro costs about $1,400 for the same volume with a more capable model and deeper search. OpenAI's web search tool, bolted onto its Responses API, costs $1,000 in tool-call fees alone at $10 per 1,000 calls — before adding the separate, variable token cost of the underlying model call and the search-result content it has to process. Google's Gemini grounding with Google Search is the most expensive of the three at this volume: at $35 per 1,000 requests beyond a 1,500-per-day free allowance, 100,000 monthly queries (averaging above that daily free threshold) costs roughly $1,925 in grounding fees alone.

What each vendor bills

OpenAI Web Search tool (OFFICIAL, OpenAI's API pricing, current as of September 2026). $10 per 1,000 calls via the Responses API, confirmed directly on OpenAI's pricing page as read in mid-September 2026 — note that some third-party trackers still cite an older or conflicting $25-per-1,000 figure, which this article treats as stale or unconfirmed against the more recent, directly-sourced $10 rate. This tool-call fee is separate from, and in addition to, the underlying model's own token cost for processing the search results and generating a response — a pattern identical to OpenAI's File Search tool (also $2.50 per 1,000 calls, covered in this site's companion managed-RAG article), where the tool fee is only one line of the real per-query cost.

Gemini grounding with Google Search (OFFICIAL, confirmed directly by Google Cloud Billing support on Google's own developer forum). 1,500 free grounding requests per day, then $35 per 1,000 requests beyond that daily allowance, billed proportionally rather than rounded up to a minimum unit — Google's own support response confirms that 10 requests over the free tier bills $0.35, not a flat $35 minimum charge. Each API call using the google_search tool counts as one billable grounding request, even if the model performs multiple underlying search queries to answer one response — a single expensive multi-search response costs the same as a single cheap one-search response, from a billing perspective.

Perplexity Sonar API (OFFICIAL, Perplexity's own pricing documentation). Bills in two parts: token cost plus a separate per-request search fee. Sonar (base model): $1 per million input tokens, $1 per million output tokens, plus $5 per 1,000 searches. Sonar Pro: $3 per million input, $15 per million output, plus $5 per 1,000 searches. Independent analysis notes that Sonar, Sonar Pro, and Sonar Reasoning Pro all carry this separate per-request search fee, ranging $5 to $14 per 1,000 requests depending on model and search depth — on a short query, this flat search fee routinely outweighs the token cost several times over, making the per-request fee, not the token rate, the dominant cost driver for most realistic query lengths.

Cost per 100,000 queries

Formula: OpenAI = (queries ÷ 1,000) × $10, tool-call fee only, excluding the separate model token cost; Gemini = max(0, (queries ÷ 30 days − 1,500 free/day)) × 30 ÷ 1,000 × $35, assuming usage is spread evenly across the month; Perplexity = (queries ÷ 1,000) × $5 search fee + token cost at an ILLUSTRATIVE 500 input / 500 output tokens per query.

At this specific volume (100,000 queries spread evenly over a month, averaging above Gemini's 1,500/day free threshold), Perplexity Sonar base is the cheapest option, OpenAI's tool-call fee alone sits in the middle (before adding its own token cost on top), and Gemini is the most expensive — though Gemini's daily free allowance means a genuinely lower-volume workload that stays under 1,500/day on every single day could cost nothing at all, a structural advantage none of this article's other two options offers.

What OpenAI's and Gemini's figures leave out

Neither OpenAI's $10-per-1,000-call fee nor Gemini's $35-per-1,000-request fee includes the underlying model's own token cost — both are bolt-on tool fees charged in addition to a separate, normal LLM API call. Perplexity's Sonar models are the only one of the three where the search fee and the token cost are both native, published parts of one unified rate card for the same product; comparing Perplexity's all-in total directly against OpenAI's or Gemini's tool-fee-only figures understates the true cost of the latter two unless their respective model token costs are added back in.

The free-tier threshold on Gemini

Formula: daily free requests = 1,500; proportional overage billing above that, per day. A workload that stays under 1,500 grounding requests on every single day — up to about 45,000 a month, evenly spread — pays nothing at all for grounding on Gemini. Because the free allowance resets daily and does not roll over or accumulate into a monthly pool, evenly distributing a fixed monthly total across every day maximizes how much of it is captured by the free tier: at 100,000 queries spread evenly (about 3,333/day), every day uses its full 1,500-request allowance before any billing starts, leaving 1,833/day billable. A bursty pattern — the same 100,000 total concentrated into fewer high-volume days with other days quiet — does worse, not better: the quiet days' free allowance goes unused entirely, while the high-volume days still only get 1,500 free requests each before the rest bills at the full $35/1,000 rate, so more of the same total monthly volume ends up billable than under even distribution.

Sensitivity

1. Query length and token consumption. Directly scales Perplexity's and the underlying model cost on OpenAI/Gemini; a longer, more complex query with more retrieved search content costs more on every platform.
2. Daily usage pattern on Gemini. A workload that can shape its traffic to stay under the 1,500/day free threshold avoids grounding fees entirely; one that is front-loaded or evenly spread above that threshold pays on every excess request.
3. Which Perplexity model tier. Sonar Pro's search fee is identical to base Sonar's ($5/1,000), but its token rate is 3x (input) to 15x (output) higher, making model choice the dominant lever on Perplexity specifically.
4. Which OpenAI web-search rate is current. The $10 versus $25 per-1,000-call conflict across sources is meaningful at volume; confirm directly against OpenAI's live pricing page.

Budgeting traps

• Pricing OpenAI's or Gemini's grounded search off the tool-call fee alone. Both require a separate, additional model token charge that this article's headline figures exclude.
• Concentrating Gemini usage into bursty, high-volume days instead of spreading it evenly. Because the daily free allowance does not roll over, bunching the same monthly total into fewer days wastes unused free quota on the quiet days and increases the total billable request count.
• Assuming Perplexity's $5-per-1,000 search fee applies to every Sonar tier. Sonar Reasoning Pro and deeper search modes were reported at up to $14 per 1,000, not the base $5 rate.
• Using a stale OpenAI web-search rate in a budget model. A still-circulating $25-per-1,000 figure conflicts with the more recently and directly sourced $10-per-1,000 rate.

What to ask before you buy

Confirm OpenAI's current web-search tool-call rate directly against its live pricing page, given the conflict between a $10 and a $25 per-1,000-call figure across sources. Model the full cost on OpenAI and Gemini by adding the underlying model's token cost to the tool-call or grounding fee, rather than budgeting off the bolt-on fee alone, since Perplexity's all-in Sonar price is not directly comparable to either vendor's partial figure.