impulse

GPT-4o Mini Search Preview

Frontier labPreview
API id gpt-4o-mini-search-previewReleased 11 Mar 2025 (Mar 2025)
Input / 1M
$0.15
at OpenAI
Output / 1M
$0.60
at OpenAI
Context window
128K
tokens
Max output
16K
tokens per reply
Hosts
1
2 listings
Released
Mar 2025
11 Mar 2025

Pricing

List prices at OpenAI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.15$0.60
Cached input
50% off input
$0.075
Batch
50% off
$0.075$0.30
Web search
$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$83.25
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$75.60
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$153
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$252
Use your own numbers

Where to run it

1 host serve GPT-4o Mini Search Preview. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
gpt-4o-mini-search-preview
$0.15 / $0.60
Show 1 more listings: regions, snapshots and variants
OpenAI
2025-03-11
gpt-4o-mini-search-preview-2025-03-11
$0.15 / $0.60

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

  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    24% less

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    24% less

Open-weight picks

  • Qwen3.8 27B
    Alibaba Qwen · on EmpirioLabs AI
    $0.17 / $0.50
    Has every key capability
    4% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    32% less
  • DeepSeek V4.1 Flash
    DeepSeek · on Sail
    $0.09 / $0.30
    Has every key capability
    46% less
  • MiMo V2.6 Flash
    Xiaomi · on GMI Cloud
    $0.112 / $0.224
    Has every key capability
    47% less

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="gpt-4o-mini-search-preview", input="Hello")
print(response.output_text)

Quick answers

How much does GPT-4o Mini Search Preview cost?

On OpenAI, GPT-4o Mini Search Preview costs $0.15 per million input tokens and $0.60 per million output tokens. Cached input costs $0.075 per million tokens.

Which APIs offer GPT-4o Mini Search Preview?

GPT-4o Mini Search Preview runs on 1 API: OpenAI.

What is GPT-4o Mini Search Preview's context window?

128K tokens, with up to 16K tokens in one reply.

Is GPT-4o Mini Search Preview being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to GPT-4o Mini Search Preview?

Models that cost less and keep most of what it can do: GPT-6 Luna on OpenAI (24% less), Claude Haiku 5.5 on Anthropic (24% less) and Qwen3.8 27B on EmpirioLabs AI (4% less). Savings are on a mix of 3 input tokens to 1 output token.

When was GPT-4o Mini Search Preview released?

OpenAI released it on 11 Mar 2025.

What is GPT-4o Mini Search Preview's API model id?

Use gpt-4o-mini-search-preview with OpenAI.

Sources

Raw catalog entry for gpt-4o-mini-search-preview on OpenAI
{
  "cache_read_input_token_cost": 7.5e-8,
  "input_cost_per_token": 1.5e-7,
  "input_cost_per_token_batches": 7.5e-8,
  "litellm_provider": "openai",
  "max_input_tokens": 128000,
  "max_output_tokens": 16384,
  "mode": "chat",
  "output_cost_per_token": 6e-7,
  "fedramp_uplift_multiplier": 1.1,
  "output_cost_per_token_batches": 3e-7,
  "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
}