Claude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MClaude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/M
BETA
Subscribe
← Back to Index·All OpenAI models
OpenAI
OpenAIEfficientLIVE INDEX

GPT-4o Search Preview

text->text

The "omni" multimodal GPT-4. Native text, vision and audio. Retired from ChatGPT in April 2026 but remains available via the API.

GPT-4o Search Preview is a efficient AI model from OpenAI. It costs $2.500 per million input tokens and $10.000 per million output tokens (blended $4.750/M), with a 128K-token context window.

Profile inherited from upstream GPT-4o ↗ — this is a hosted variant of the same open-weights model.

Released May 2024Modalities text, vision, audioOfficial model page ↗Provider pricing ↗API docs ↗Pricing source ↗Compare with another model →Estimate monthly cost →
INPUT
$2.500/M
per million input tokens
OUTPUT
$10.000/M
per million output tokens
BLENDED 70/30
$4.750/M
default reference rate · how it's calculated →
CONTEXT
128K
128,000 tokens
What it's good at
  • Native audio + vision
  • Fast
  • Wide ecosystem support
Typical use cases
  • Voice apps
  • Vision QA
  • Legacy GPT-4o pipelines
Benchmarks
vs. best public score
Scores inherited from GPT-4o — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU88%
Multitask academic knowledge across 57 subjects.
GPQA Diamond53%
Graduate-level science questions, "Google-proof".
MATH76%
High-school competition math problems.
HumanEval90%
Python function synthesis from docstrings.
SWE-bench Verified33%
Real GitHub issues solved end-to-end.
LMArena Elo1316 Elo
Crowd-sourced head-to-head preference Elo rating.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources — treat as directional rather than authoritative.
More from OpenAI
See all 25 →
GPT-5.5
Frontier · 1M ctx
in $5.000/Mout $30.000/M
GPT-5.2
Frontier · 400K ctx
in $1.750/Mout $14.000/M
GPT-5.2-Codex
Coding · 400K ctx
in $1.750/Mout $14.000/M
GPT-5
Frontier · 400K ctx
in $1.250/Mout $10.000/M
GPT-4.1
Frontier · 1M ctx
in $2.000/Mout $8.000/M
GPT-4.1 mini
Efficient · 1M ctx
in $0.400/Mout $1.600/M
Frequently asked questions

How much does GPT-4o Search Preview cost?

GPT-4o Search Preview costs $2.500 per million input tokens and $10.000 per million output tokens, for a blended reference rate of $4.750 per million tokens.

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

GPT-4o Search Preview supports up to 128K tokens of context (128,000 tokens).

What is GPT-4o Search Preview best for?

GPT-4o Search Preview is well suited to Native audio + vision, Fast and Wide ecosystem support.

Who makes GPT-4o Search Preview?

GPT-4o Search Preview is developed and served by OpenAI. It was released in May 2024.