GPT-6.1 Sol

Specifications

Official API ID

gpt-6.1-sol

Documented version

gpt-6.1-sol

Status

active

Shared context window

1,050,000

Input token limit

922,000

Maximum output

128,000

Input types

text, image

Output types

text

Reasoning

yes

Structured output

yes

Function calling

yes

Streaming

yes

Released

Not verified

Limits are documented separately; an unknown input limit does not mean unlimited input. Availability depends on your provider account and region.

Text token pricing

USD per 1 million tokens · Standard paid tier

Input

$2.00

Output (including thinking)

$10.00

Cached input read

$0.10

Default cache write

$2.50

5-minute cache write

Not verified

1-hour cache write

Not verified

Above 272,000 input tokens, full-request rates become $4.00 input / $15.00 output / $0.20 cache read.

Text tokens only. Billable output includes reasoning tokens where applicable. Excludes cache creation, tools, media and regional or processing-tier uplifts.

Default 30-minute cache writes use 1.25× uncached input pricing as a replacement rate. V1 live trials request explicit-only caching with no breakpoints.