GPT-5
- Context
- 400K
- 128K max output
- Input price
- $1.25
- per 1M tokens · OpenAI API
- Output price
- $10.00
- per 1M tokens
- Epoch Capabilities Index
- 150
- #42 of 71 listed
- LMArena Text
- 1,435
- #55 of 79 listed
Where to run it
3 offerings · prices as listed| Meter | Tier | Price |
|---|---|---|
| Input | Standard | $1.25 / 1M tokens |
| Batch | $0.63 / 1M tokens | |
| Flex tier | $0.63 / 1M tokens | |
| Fast tier | $2.50 / 1M tokens | |
| Output | Standard | $10.00 / 1M tokens |
| Batch | $5.00 / 1M tokens | |
| Flex tier | $5.00 / 1M tokens | |
| Fast tier | $20.00 / 1M tokens | |
| Cache read | Standard | $0.13 / 1M tokens |
| Batch | $0.063 / 1M tokens | |
| Flex tier | $0.063 / 1M tokens | |
| Fast tier | $0.25 / 1M tokens | |
| Input | Standard | $1.25 / 1M tokens |
| Batch | $0.63 / 1M tokens | |
| Output | Standard | $10.00 / 1M tokens |
| Batch | $5.00 / 1M tokens | |
| Cache read | Standard | $0.13 / 1M tokens |
| Batch | $0.070 / 1M tokens | |
| Input | Standard | $1.38 / 1M tokens |
| Batch | $0.69 / 1M tokens | |
| Output | Standard | $11.00 / 1M tokens |
| Batch | $5.50 / 1M tokens | |
| Cache read | Standard | $0.14 / 1M tokens |
| Batch | $0.070 / 1M tokens | |
Changes
All changes →- 9 new prices on OpenAI API Input (Batch) $0.63 · Cache read (Batch) $0.063 · Output (Batch) $5.00 · Input (Flex tier) $0.63 · +5 more
- Now priced on Azure OpenAI in Foundry, data-zone Input $1.38 · Cache read $0.14 · Output $11.00
- Now priced on Azure OpenAI in Foundry Input $1.25 · Cache read $0.13 · Output $10.00
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 150
#42 of 71 listed models · CI 0–0
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 1,435
#55 of 79 listed models · high effort · CI 1,430–1,439 · 31,503 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 55.4%
#35 of 56 listed models · high effort · ±2.95
Also listed: low effort 37.2% · minimal effort 18.2%
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 86.2%
#43 of 64 listed models · high effort · ±2.08
Also listed: medium effort 85.4% · minimal effort 71.7%
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 73.6%
#17 of 23 listed models · high effort · ±2.01
Also listed: medium effort 71.5%
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 1,451
#59 of 79 listed models · high effort · CI 1,438–1,464 · 2,212 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 1,470
#59 of 79 listed models · high effort · CI 1,462–1,478 · 6,353 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 25, 2026 · changes we made
- LMArena Vision 1,209
#42 of 49 listed models · high effort · CI 1,202–1,216 · 34,351 votes
LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Sep 13, 2026 · changes we made