GPT-4o Search Preview
gpt-4o-search-previewReleased 11 Mar 2025 (Mar 2025)Pricing
List prices at OpenAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $2.50 | $10.00 | |
| Cached input 50% off input | $1.25 | 50% off input | |
| Batch 50% off | $1.25 | $5.00 | 50% off |
| Web search $25.00 per 1,000 searches | $25.00 per 1,000 searches |
What it costs a month
At OpenAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$1,388
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$1,260
- Coding agent1,000 requests a day, 40K in / 2K out, cached$2,550
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$4,200
Where to run it
1 host serve GPT-4o Search Preview. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
OpenAILab API gpt-4o-search-preview | $2.50 / $10.00 | gpt-4o-search-preview |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| OpenAI | |||||||
| 2025-03-11 gpt-4o-search-preview-2025-03-11 | $2.50 / $10.00 | gpt-4o-search-preview-2025-03-11 | |||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImagesPDFs
- Produces
- Text
- Features
- Parallel tool callsPDF inputPrompt cachingBuilt-in web search
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than OpenAI.
Smaller OpenAI models
- 9% less
- 54% less
- 61% less
Other frontier labs
- 9% less
- 9% less
- 31% less
- 9% less
Open-weight picks
- 9% less
- 49% less
- 61% less
- 88% less
Call it
Using OpenAI's API.
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY
response = client.responses.create(model="gpt-4o-search-preview", input="Hello")
print(response.output_text)curl https://api.openai.com/v1/responses \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-4o-search-preview", "input": "Hello"}'from litellm import completion
response = completion(
model="openai/gpt-4o-search-preview",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does GPT-4o Search Preview cost?
On OpenAI, GPT-4o Search Preview costs $2.50 per million input tokens and $10.00 per million output tokens. Cached input costs $1.25 per million tokens.
Which APIs offer GPT-4o Search Preview?
GPT-4o Search Preview runs on 1 API: OpenAI.
What is GPT-4o Search Preview's context window?
128K tokens, with up to 16K tokens in one reply.
Is GPT-4o Search Preview being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to GPT-4o Search Preview?
Models that cost less and keep most of what it can do: GPT-6.2 Sol on OpenAI (9% less), Gemini 4 Carbon on Google AI Studio (9% less), Claude Sonnet 5.5 on Anthropic (9% less) and Kimi K3.1 Pro on Databricks (9% less). Savings are on a mix of 3 input tokens to 1 output token.
When was GPT-4o Search Preview released?
OpenAI released it on 11 Mar 2025.
What is GPT-4o Search Preview's API model id?
Use gpt-4o-search-preview with OpenAI.
Sources
Raw catalog entry for gpt-4o-search-preview on OpenAI
{
"cache_read_input_token_cost": 0.00000125,
"input_cost_per_token": 0.0000025,
"input_cost_per_token_batches": 0.00000125,
"litellm_provider": "openai",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 0.00001,
"fedramp_uplift_multiplier": 1.1,
"output_cost_per_token_batches": 0.000005,
"search_context_cost_per_query": {
"search_context_size_high": 0.025,
"search_context_size_low": 0.025,
"search_context_size_medium": 0.025
},
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
}