gpt-4o-search-preview API pricing
Blended at 3:1 input to output: $4.38 per million tokens.
OpenAI charges $2.50 per million input tokens and $10.00 per million output tokens. 2 of the models nearest it in price are cheaper on a blended basis.
Against the models nearest in price
Blended at a 3:1 input to output ratio.
| Source | ||||||
|---|---|---|---|---|---|---|
| gpt-4o-search-preview This model | OpenAI | $2.50 | $10.00 | 128,000 | $4.38 | ↗ |
| command-a-03-2025 | Cohere | $2.50 | $10.00 | 256,000 | $4.38 | ↗ |
| gpt-4o | OpenAI | $2.50 | $10.00 | 128,000 | $4.38 | ↗ |
| gpt-4o-audio-preview | OpenAI | $2.50 | $10.00 | 128,000 | $4.38 | ↗ |
| gpt-5.6-terra | OpenAI | $2.00 | $12.00 | 922,000 | $4.50 | ↗ |
| claude-sonnet-5 | Anthropic | $2.00 | $10.00 | 1,000,000 | $4.00 | ↗ |
| gpt-5.6-sol | OpenRouter | $2.00 | $10.00 | 1,050,000 | $4.00 | ↗ |
| gpt-5.2 | OpenAI | $1.75 | $14.00 | 272,000 | $4.81 | ↗ |
| gpt-5.2-chat | OpenRouter | $1.75 | $14.00 | 128,000 | $4.81 | ↗ |
Last checked . Methodology
Questions
How much does gpt-4o-search-preview cost per million tokens?
$2.50 per million input tokens and $10.00 per million output tokens, with cached input at $1.25. At a 3:1 input to output mix that blends to $4.38. Checked 12 Sept 2026.
What would gpt-4o-search-preview cost for a real workload?
A thousand requests a day at 2,000 input and 600 output tokens each comes to $330.00 a month.
What is the context window for gpt-4o-search-preview?
128,000 tokens of input, with up to 16,384 tokens of output.
command-a-03-2025 · gpt-4o · gpt-4o-audio-preview · gpt-5.6-terra · claude-sonnet-5 · All OpenAI models · Cost calculator