AiCostCompare

GPT-5.1

by OpenAI · openai/gpt-5.1 · #245 cheapest of 325 paid models

Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...

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

Pricing

Input

$1.25

per 1M tokens

Output

$10.00

per 1M tokens

Blended (3:1)

$3.44

3 input : 1 output

Cache read

$0.125

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for GPT-5.1 with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$3.44$0.1375
50%$3.02$0.0813−41%
90%$2.68$0.0362−74%

*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$0.003625$3.62
Document summary8,0001,000$0.02$20.00
Codebase question (RAG)30,0002,000$0.0575$57.50
Long-context analysis150,0005,000$0.2375$237.50

Performance

Intelligence Index

36.9

AA composite quality

Coding Index

49.4

Math Index

94

Agentic Index

21

Output speed

110 tok/s

median

Time to first token

39.50s

median

Time to first answer

39.50s

after reasoning tokens

Artificial Analysis benchmarks

BenchmarkScore
MMLU-Pro87.0%
GPQA Diamond87.3%
Humanity's Last Exam26.5%
LiveCodeBench86.8%
SciCode43.3%
AIME 202594.0%
IFBench72.9%
AA-LCR (Long Context Reasoning)75.0%
Terminal-Bench Hard45.5%
Terminal-Bench 2.152.4%
τ²-Bench (Telecom)81.9%
τ³-Bench Banking14.0%

Design Arena Elo

CategoryElo
Website1,215
Web apps1,075
Mobile apps1,122
UI components1,209
Data viz1,241
SVG1,196
3D1,120
Game dev1,237
Code categories1,204
ASCII art1,160

Specs

Context window

400K

tokens

Max output

128K

tokens

Input modalities

image, text, file

Tokenizer

GPT