GPT-5.4
Official information
- Release date
- Mar 5, 2026
- Official model ID
- gpt-5.4
- Vendor source
- GPT-5.4
- Identity verified
- Aug 13, 2026
API pricing
- Verification
- Retained last valid price
- Verified at
- Value benchmark tier
- Fixed USD rate
| Tier / region | Input / output · per MTok | Context pricing tier | Billing | Validity | Source |
|---|---|---|---|---|---|
| Fixed USD rate | $2.5 / $15 | — | PAYG | — | Official rates |
Rankings by category
Overall
#13High 0.9170.6
| Source | Percentile | Raw score | Config folding |
|---|---|---|---|
| Epoch AI | 79.3 | 156.9 | Single config |
| LiveBench | 74.4 | 78.8 | Single config |
| LMArena | 58.0 | 1461.1 | Median of 2 configs |
Cross-source percentile spread 21.4
Coding
#21High 0.7748.7
| Source | Percentile | Raw score | Config folding |
|---|---|---|---|
| DeepSWE | 37.5 | 51.8 | Single config |
| LiveBench | 67.1 | 63.3 | Single config |
| LMArenatext-coding | 60.2 | 1487.8 | Median of 2 configs |
| · webdev | 22.8 | 1442.6 | Median of 3 configs |
Cross-source percentile spread 29.6
Agent
#20High 0.9442.6
| Source | Percentile | Raw score | Config folding |
|---|---|---|---|
| Agents' Last Exam | 38.6 | 33.0 | Median of 2 configs |
| DeepSWE | 37.5 | 51.8 | Single config |
| LMArena | 51.7 | 0.0 | Single config |
Cross-source percentile spread 14.2
Reasoning
#12High 0.9366.9
| Source | Percentile | Raw score | Config folding |
|---|---|---|---|
| Epoch AI | 63.4 | 0.9 | Median of 5 configs |
| LiveBench | 76.8 | 91.1 | Single config |
| LMArenatext-math | 63.1 | 1473.7 | Median of 2 configs |
| · text-hard | 58.0 | 1477.3 | Median of 2 configs |
Cross-source percentile spread 16.3
Value
#20High 0.9142.5
Aliases & configurations
- gpt-5-4
- gpt-5-4-2026-03-05
- gpt-5-4-high· high
- gpt-5-4-high-codex-harness· high / codex harness
- gpt-5-4-medium-codex-harness· medium / codex harness
- gpt-5-4-xhigh· xhigh