GPT-5.4
- Context
- 1.05M
- 128K max output
- Input price
- $2.50
- per 1M tokens · OpenAI API
- Output price
- $15.00
- per 1M tokens
- Epoch Capabilities Index
- 156.9
- #14 of 71 listed
- LMArena Text
- 1,475
- #24 of 79 listed
Where to run it
3 offerings · prices as listed| Meter | Tier | Price |
|---|---|---|
| Input | Standard | $2.50 / 1M tokens |
| Batch | $1.25 / 1M tokens | |
| Flex tier | $1.25 / 1M tokens | |
| Fast tier | $5.00 / 1M tokens | |
| Prompts over 272K tokens | $5.00 / 1M tokens | |
| Prompts over 272K tokens · Batch | $2.50 / 1M tokens | |
| Prompts over 272K tokens · Flex tier | $2.50 / 1M tokens | |
| Output | Standard | $15.00 / 1M tokens |
| Batch | $7.50 / 1M tokens | |
| Flex tier | $7.50 / 1M tokens | |
| Prompts over 272K tokens | $22.50 / 1M tokens | |
| Fast tier | $30.00 / 1M tokens | |
| Prompts over 272K tokens · Batch | $11.25 / 1M tokens | |
| Prompts over 272K tokens · Flex tier | $11.25 / 1M tokens | |
| Cache read | Standard | $0.25 / 1M tokens |
| Batch | $0.13 / 1M tokens | |
| Flex tier | $0.13 / 1M tokens | |
| Fast tier | $0.50 / 1M tokens | |
| Prompts over 272K tokens | $0.50 / 1M tokens | |
| Prompts over 272K tokens · Batch | $0.25 / 1M tokens | |
| Prompts over 272K tokens · Flex tier | $0.25 / 1M tokens | |
| Input | Standard | $2.50 / 1M tokens |
| Batch | $1.25 / 1M tokens | |
| Priority tier | $5.00 / 1M tokens | |
| Prompts over 272K tokens | $5.00 / 1M tokens | |
| Output | Standard | $15.00 / 1M tokens |
| Batch | $7.50 / 1M tokens | |
| Prompts over 272K tokens | $22.50 / 1M tokens | |
| Priority tier | $30.00 / 1M tokens | |
| Cache read | Standard | $0.25 / 1M tokens |
| Batch | $0.13 / 1M tokens | |
| Priority tier | $0.50 / 1M tokens | |
| Prompts over 272K tokens | $0.50 / 1M tokens | |
| Input | Standard | $2.75 / 1M tokens |
| Priority tier | $5.50 / 1M tokens | |
| Output | Standard | $16.50 / 1M tokens |
| Priority tier | $33.00 / 1M tokens | |
| Cache read | Standard | $0.28 / 1M tokens |
| Priority tier | $0.55 / 1M tokens | |
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 156.9
#14 of 71 listed models · CI 155.1–159.3
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 1,475
#24 of 79 listed models · high effort · CI 1,471–1,479 · 64,479 votes
Also listed: gpt-5.4 1,465
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 78.6%
#12 of 56 listed models · xhigh effort · ±2.43
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 93.3%
#12 of 64 listed models · xhigh effort · ±1.8
Also listed: high effort 89.9% · medium effort 88.9% · low effort 84.8% · reasoning off 74.7%
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 · SWE-bench Verified 76.9%
#7 of 23 listed models · high effort · ±1.92
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 1,507
#31 of 79 listed models · high effort · CI 1,497–1,517 · 4,159 votes
Also listed: gpt-5.4 1,493
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Text · Coding 1,521
#22 of 79 listed models · high effort · CI 1,515–1,526 · 17,577 votes
Also listed: gpt-5.4 1,511
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Vision 1,302
#10 of 49 listed models · high effort · CI 1,296–1,308 · 25,357 votes
Also listed: gpt-5.4 1,293
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 13, 2026 · changes we made