OpenAI Web Search Cost Calculator
Estimate the OpenAI web search tool bill. Enter monthly search calls, search content tokens per call, prompt and output tokens, and pick a model. Total = calls ÷ 1,000 × $10 (or $25 for preview non-reasoning) + content tokens × model input rate + prompt/output tokens. Compare against the model-only cost. Estimates only; official OpenAI pricing prevails.
Math runs in your browser. Nothing is uploaded.
Custom $/1M rates (optional)
Monthly USD
—
Tool call fee
—
Search content tokens
—
Model tokens only (no search)
—
Total ÷ model-only
—
Estimates only; official vendor pricing prevails (2026-10-30). Total = calls ÷ 1,000 × tool fee + calls × content tokens × model input rate + prompt/output tokens at model rates. Preview non-reasoning: $25/1k and content tokens free.Official pricing: OpenAI
Gemini Grounding Cost Calculator · OpenAI Token Cost Calculator · AI Agent Cost Calculator · RAG Cost Calculator
More in this group
- Web Search API Cost Comparison Exa vs Tavily vs Firecrawl.
- Exa API Cost Calculator Exa search, contents & Agent cost.
- Tavily API Cost Calculator Tavily credits → cheapest plan.
- Google Custom Search API Migration Cost Calculator Google CSE shutdown → alternatives cost.
- Brave Search API Cost Calculator Brave Search & Answers cost.
- Firecrawl API Cost Calculator Firecrawl credits → cheapest plan.
- SerpApi Cost Calculator SerpApi searches → cheapest plan.
- Serper API Cost Calculator Serper credits → cheapest pack.
How it works
- How is OpenAI web search cost calculated?
- Total = calls ÷ 1,000 × tool fee + calls × search content tokens × model input rate + calls × (prompt × input + output × output rate). Example: 10,000 calls, GPT-6.1 Terra ($1 / $5), 5,000 content + 1,000 prompt + 500 output tokens per call → $100 tool fee + $50 content + $35 model = $185 vs $35 model-only.
- How much does a web search call cost?
- $10 per 1,000 calls for the web search tool on all models (and preview on reasoning models). Web search preview on non-reasoning models is $25 per 1,000 calls, with search content tokens free.
- What are search content tokens?
- Tokens retrieved from the search index and fed to the model alongside your prompt. They are billed at the chosen model’s input rate. For gpt-4o-mini and gpt-4.1-mini with the non-preview tool, content is billed as a fixed 8,000 input tokens per call.
- How does this compare to Gemini Grounding?
- Gemini Grounding with Google Search gives 5,000 free requests per month, then $14 per 1,000. Use the Gemini Grounding calculator for that side of the comparison.
- Are results exact?
- No. Content token counts vary per query. Estimates only; official OpenAI pricing prevails.