GoTry AI

GPT-5.6 Sol

Language OpenAI Available Released Jul 9, 2026 Partly verified
Model ID
Context
1.05M
128K max output
Input price
$4.00
per 1M tokens · OpenAI API
Output price
$20.00
per 1M tokens
Epoch Capabilities Index
162
#6 of 71 listed
LMArena Text
1,483
#14 of 79 listed

Where to run it

3 offerings · prices as listed
MeterTierPrice
OpenAI API (opens in a new tab) Official Global · USD gpt-5.6-sol
InputStandard $4.00 / 1M tokens
Batch $2.00 / 1M tokens
Flex tier $2.00 / 1M tokens
Fast tier $8.00 / 1M tokens
OutputStandard $20.00 / 1M tokens
Batch $10.00 / 1M tokens
Flex tier $10.00 / 1M tokens
Fast tier $40.00 / 1M tokens
Cache readStandard $0.40 / 1M tokens
Batch $0.20 / 1M tokens
Flex tier $0.20 / 1M tokens
Fast tier $0.80 / 1M tokens
Cache writeStandard $5.00 / 1M tokens
Batch $2.50 / 1M tokens
Flex tier $2.50 / 1M tokens
Fast tier $10.00 / 1M tokens
InputStandard $4.00 / 1M tokens
Priority tier $8.00 / 1M tokens
OutputStandard $20.00 / 1M tokens
Priority tier $40.00 / 1M tokens
Cache readStandard $0.40 / 1M tokens
Priority tier $0.80 / 1M tokens
Cache writeStandard $5.00 / 1M tokens
Priority tier $10.00 / 1M tokens
Azure OpenAI in Foundry (opens in a new tab) data-zone · USD gpt-5-6-sol
InputStandard $4.40 / 1M tokens
Priority tier $8.80 / 1M tokens
OutputStandard $22.00 / 1M tokens
Priority tier $44.00 / 1M tokens
Cache readStandard $0.44 / 1M tokens
Priority tier $0.88 / 1M tokens
Cache writeStandard $5.50 / 1M tokens
Priority tier $11.00 / 1M tokens
  1. 8 prices dropped on OpenAI API Input (Prompts over 272K tokens) $8.00 · Output (Prompts over 272K tokens) $30.00 · Cache read (Prompts over 272K tokens) $0.80 · Input (Prompts over 272K tokens, Fast tier) $16.00 · +4 more

Vendor-reported scores

Published by OpenAI, under the conditions it states
BenchmarkSettingScore
SWE-bench Pro—64.6%
DeepSWE 1.1—72.7%
Terminal-Bench 2.1single agent88.8%
ultra (multi-agent, 4 agents)91.9%
OSWorld 2.0set and scoring not stated62.6%
v2026.08.08 offline set, partial score; maximum across effort levels65.7%
BrowseCompsingle agent90.4%
ultra (multi-agent, 4 agents)92.2%
GPQA Diamond—94.6%
MMMU-Prono tools83%
with tools84.6%
MRCR v28-needle, 256K–512K91.5%
8-needle, 512K–1M73.8%
Terminal-Bench 4.0maximum across effort levels37.3%

Cited scores

From third-party leaderboards, not measured by us
  • Epoch Capabilities Index 162

    #6 of 71 listed models · CI 159.6–165.9

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • LMArena Text 1,483

    #14 of 79 listed models · xhigh effort · CI 1,479–1,488 · 34,258 votes

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made

  • Epoch AI · FrontierMath Tiers 1–3 89.1%

    #3 of 56 listed models · max effort · ±1.85

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • Epoch AI · GPQA Diamond 93.5%

    #9 of 64 listed models · max effort · ±1.57

    Also listed: low effort 89.9% · reasoning off 82.8%

    Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Sep 26, 2026 · changes we made

  • LMArena Text · Chinese 1,538

    #8 of 79 listed models · xhigh effort · CI 1,526–1,550 · 2,675 votes

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made

  • LMArena Text · Coding 1,531

    #14 of 79 listed models · xhigh effort · CI 1,524–1,538 · 9,391 votes

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made

  • LMArena Vision 1,280

    #20 of 49 listed models · xhigh effort · CI 1,272–1,289 · 7,729 votes

    LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 13, 2026 · changes we made