AiCostCompare

o3 (batch)

by OpenAI · openai/o3:batch · #288 cheapest of 422 paid models

Prices updated Sep 19, 2026, 9:36 PM UTC · refreshed hourly

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash

Pricing

Input

$1.00

per 1M tokens

Output

$4.00

per 1M tokens

Blended (3:1)

$1.75

3 input : 1 output

Cache read

$0.25

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for o3 (batch) with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$1.75$0.106
50%$1.47$0.0685−35%
90%$1.24$0.0385−64%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.0017$1.70
Document summary8,0001,000$0.012$12.00
Codebase question (RAG)30,0002,000$0.038$38.00
Long-context analysis150,0005,000$0.17$170.00

Performance

Intelligence Index

20.2

AA composite quality

Coding Index

Math Index

88.3

Agentic Index

Output speed

136 tok/s

median

Time to first token

5.43s

median

Time to first answer

5.43s

after reasoning tokens

Artificial Analysis benchmarks

BenchmarkScore
MMLU-Pro85.3%
GPQA Diamond82.7%
Humanity's Last Exam20.1%
LiveCodeBench80.8%
MATH-50099.2%
AIME90.3%
AIME 202588.3%
IFBench71.4%
AA-LCR (Long Context Reasoning)74.7%
Terminal-Bench Hard37.1%
τ²-Bench (Telecom)80.7%

Design Arena Elo

CategoryElo
Website1,048
UI components1,032
Data viz1,200
Game dev1,058
Code categories1,035

Specs

Context window

200K

tokens

Max output

100K

tokens

Input modalities

image, text, file

Tokenizer

GPT