AiCostCompare

GPT-5.1 (batch)

by OpenAI · openai/gpt-5.1:batch · #285 cheapest of 422 paid models

Prices updated Sep 19, 2026, 6:21 PM 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

$0.625

per 1M tokens

Output

$5.00

per 1M tokens

Blended (3:1)

$1.72

3 input : 1 output

Cache read

$0.063

per 1M cached tokens

Cache write

per 1M tokens

Cache & batch economics

Effective prices for GPT-5.1 (batch) with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$1.72$0.0688
50%$1.51$0.0406−41%
90%$1.34$0.0181−74%

*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$0.001812$1.81
Document summary8,0001,000$0.01$10.00
Codebase question (RAG)30,0002,000$0.0287$28.75
Long-context analysis150,0005,000$0.1187$118.75

Performance

Intelligence Index

24.7

AA composite quality

Coding Index

49.4

Math Index

94

Agentic Index

Output speed

0 tok/s

median

Time to first token

0s

median

Time to first answer

0s

after reasoning tokens

Artificial Analysis benchmarks

BenchmarkScore
MMLU-Pro87.0%
GPQA Diamond87.3%
Humanity's Last Exam28.5%
LiveCodeBench86.8%
AIME 202594.0%
IFBench72.9%
AA-LCR (Long Context Reasoning)80.0%
Terminal-Bench Hard45.5%
Terminal-Bench 2.152.4%
τ²-Bench (Telecom)81.9%
τ³-Bench Banking15.9%

Design Arena Elo

CategoryElo
Website1,199
UI components1,181
Data viz1,219
SVG1,173
3D1,090
Game dev1,202
Code categories1,186
ASCII art1,137

Specs

Context window

400K

tokens

Max output

128K

tokens

Input modalities

image, text, file

Tokenizer

GPT