Choose from the models that matter.

Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows

Context

400,000

Providers

11

Input / 1M

$18.9

Output / 1M

$150

Chat-tuned GPT model for conversational assistance, writing, and tool workflows

Context

400,000

Providers

5

Input / 1M

$1.75

Output / 1M

$14

Coding-optimized GPT model for repository edits, reviews, and agentic software work

Context

400,000

Providers

23

Input / 1M

$1.6

Output / 1M

$13

Agent-ready GPT for coding and computer-use workflows at a lower cost

Context

1,050,000

Providers

33

Input / 1M

$1.8

Output / 1M

$10.8

Strong small GPT for coding subagents, quick tool use, and high-volume work

Context

400,000

Providers

27

Input / 1M

$0

Output / 1M

$0

Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation

Context

1,047,576

Providers

24

Input / 1M

$0.18

Output / 1M

$1.1

More exact GPT-5.4 tier for demanding professional reasoning and agent tasks

Context

1,050,000

Providers

14

Input / 1M

$27

Output / 1M

$160

Default frontier GPT for coding, computer use, research, and knowledge work

Context

1,050,000

Providers

33

Input / 1M

$0

Output / 1M

$0

Compact GPT model for low-latency assistance and high-volume workloads

Context

400,000

Providers

1

Input / 1M

$5

Output / 1M

$30

Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding

Context

1,050,000

Providers

11

Input / 1M

$27.2727

Output / 1M

$163.6364

Cost-efficient GPT-5.6 model for fast, high-volume workloads

Context

1,050,000

Providers

16

Input / 1M

$0.7

Output / 1M

$4.2

Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows

Context

1,050,000

Providers

16

Input / 1M

$2.5

Output / 1M

$15