Reliable GPT generation for broad coding, writing, and tool-assisted product work
Specification
openai listing
Context
400K
Max output
128K
Released
2025-12-11
Knowledge cutoff
2025-08-31
Retires
2027-06-08
Open weights
no
Input
text, image
Output
text
Price
US dollars per million tokens · openai list price
Input
$1.75
Output
$14.00
Cache read
$0.175
Cache write
$1.75
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | openai | $0.875 |
| Batch output | openai | $7.00 |
| Priority input | azure | $3.50 |
| Priority output | azure | $28.00 |
Batch input is 50% below the interactive input price at the same listing.
Quality
12 benchmarks · 3 sources
Composite
79th
percentile of 334 scored models
Rank
70 / 334
±0.06 sd
Evidence
12 × 3
3 or more benchmarks, from 2 or more sources
Effort range
14.3
points between effort settings
coding73rd1/3 bench
reasoning84th4/4 bench
math82nd5/7 bench
knowledge34th1/1 bench
general45th1/1 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| xhigh | 86th | 9 |
| high | 84th | 9 |
| medium | 84th | 7 |
| low | 63rd | 7 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| Chess Puzzles | 49.0 ±5.0 | xhigh | Epoch AI | 2025-12-15 |
| ↳ | 40.0 ±4.9 | high | Epoch AI | 2025-12-11 |
| ↳ | 40.0 ±4.9 | medium | Epoch AI | 2025-12-11 |
| ↳ | 23.0 ±4.2 | low | Epoch AI | 2025-12-11 |
| Settings differ by 26.0 points on this benchmark. | ||||
| OTIS Mock AIME 2024-2025 | 96.1 ±2.6 | high | Epoch AI | 2025-12-11 |
| ↳ | 96.1 ±2.7 | xhigh | Epoch AI | 2025-12-13 |
| ↳ | 93.9 ±3.1 | medium | Epoch AI | 2025-12-11 |
| ↳ | 78.9 ±5.0 | low | Epoch AI | 2025-12-11 |
| Settings differ by 17.2 points on this benchmark. | ||||
| GPQA diamond | 91.4 ±1.8 | xhigh | Epoch AI | 2025-12-13 |
| ↳ | 88.2 ±1.9 | high | Epoch AI | 2025-12-11 |
| ↳ | 87.9 ±1.9 | medium | Epoch AI | 2025-12-11 |
| ↳ | 82.7 ±2.3 | low | Epoch AI | 2025-12-11 |
| Settings differ by 8.7 points on this benchmark. | ||||
| FrontierMath-v1 | 50.2 ±2.9 | high · 2 runs | Epoch AI | 2025-12-11 |
| ↳ | 48.5 ±16.3 | medium · 2 runs | Epoch AI | 2025-12-11 |
| ↳ | 40.7 ±2.9 | xhigh | Epoch AI | 2025-12-13 |
| ↳ | 33.3 ±2.6 | low · 2 runs | Epoch AI | 2025-12-11 |
| Settings differ by 16.9 points on this benchmark. | ||||
| FrontierMath-Tiers-1-3-v2 | 67.4 ±2.8 | xhigh | Epoch AI | 2026-06-11 |
| SWE-Bench verified | 73.8 ±2.0 | high | Epoch AI | 2026-02-12 |
| ↳ | 72.3 | high · mini-SWE-agent · 2 runs | SWE-bench | — |
| ↳ | 69.0 | default · mini-SWE-agent | SWE-bench | — |
| Sources and settings disagree by 4.8 points. Both figures stand. | ||||
| Mystery Game Puzzles | 23.0 ±4.2 | high | Epoch AI | 2026-08-06 |
| ↳ | 22.0 ±4.2 | medium | Epoch AI | 2026-08-28 |
| ↳ | 10.0 ±3.0 | low | Epoch AI | 2026-08-27 |
| Settings differ by 13.0 points on this benchmark. | ||||
| LiveBench | 75.2 | high · 23 runs | LiveBench | 2026-06-25 |
| FrontierMath-Tier-4-2025-07-01 | 18.8 ±5.6 | xhigh | Epoch AI | 2025-12-14 |
| ↳ | 9.4 ±0.0 | high · 2 runs | Epoch AI | 2025-12-11 |
| ↳ | 8.3 ±5.4 | medium · 2 runs | Epoch AI | 2025-12-11 |
| ↳ | 3.1 ±0.0 | low · 2 runs | Epoch AI | 2025-12-11 |
| Settings differ by 15.7 points on this benchmark. | ||||
| FrontierMath-Tier-4-v2 | 31.7 ±7.3 | xhigh | Epoch AI | 2026-06-11 |
| EBR-bench | 23.0 | xhigh | Epoch AI | 2026-06-26 |
| SimpleQA Verified | 37.1 ±1.5 | xhigh | Epoch AI | 2026-08-27 |
| ↳ | 34.3 ±1.5 | high | Epoch AI | 2026-08-27 |
| ↳ | 32.8 ±1.5 | low | Epoch AI | 2026-08-27 |
| ↳ | 32.7 ±1.5 | medium | Epoch AI | 2026-08-27 |
| Settings differ by 4.4 points on this benchmark. | ||||
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 34 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| openaivendor | $1.75 | $14.00 | $0.175 | — | 400K 272K | 128K | — |
| qihang-ai | $0.25 | $2.00 | — | — | 400K | 128K | — |
| unorouter | $1.05 | $8.40 | — | — | 400K | 128K | — |
| sap-ai-core | $1.25 | $9.44 | $0.12 | — | 400K | 128K | — |
| jiekou | $1.575 | $12.60 | — | — | 400K | 128K | — |
| poe | $1.60 | $13.00 | $0.16 | — | 400K | 128K | — |
| 302ai | $1.75 | $14.00 | — | — | 400K | 128K | — |
| abacus | $1.75 | $14.00 | $0.175 | — | 400K | 128K | — |
| aihubmix | $1.75 | $14.00 | $0.175 | — | 400K | 128K | — |
| azure | $1.75 | $14.00 | $0.125 $0.175 | — | 400K 272K | 128K | 2027-06-08 |
| azure-cognitive-services | $1.75 | $14.00 | $0.125 | — | 400K | 128K | — |
| databricks | $1.75 | $14.00 | $0.175 | $1.75 | 400K 272K | 128K | — |
| edenai | $1.75 | $14.00 | $0.175 | — | 400K | 128K | — |
| gmi · gmi | $1.75 | $14.00 | — | — | 410K | 32K | — |
| impossibl | $1.75 | $14.00 | $0.175 | — | 400K | 128K | — |
| kilo | $1.75 | $14.00 | $0.175 | — | 400K | 128K | — |
| llmgateway | $1.75 | $14.00 | $0.175 | — | 400K | 128K | — |
| llmgateway-providers | $1.75 | $14.00 | $0.175 | — | 400K | 128K | — |
| merge-gateway | $1.75 | $14.00 | $0.175 | — | 400K | 128K | — |
| nano-gpt | $1.75 | $14.00 | $0.175 | — | 400K | 128K | — |
| nearai | $1.75 | $14.00 | $0.175 | — | 400K | 128K | — |
| neon | $1.75 | $14.00 | $0.175 | — | 400K | 128K | — |
| ofox | $1.75 | $14.00 | $0.18 | — | 400K | 128K | — |
| opencode | $1.75 | $14.00 | $0.175 | — | 400K | 128K | — |
| openrouter | $1.75 | $14.00 | $0.175 | — | 400K 272K | 128K | — |
| orcarouter | $1.75 | $14.00 | $0.175 | — | 400K | 128K | — |
| perplexity | $1.75 | $14.00 | $0.175 | — | — | — | — |
| perplexity-agent | $1.75 | $14.00 | $0.175 | — | 400K | 128K | — |
| vercel | $1.75 | $14.00 | $0.175 | — | 400K | 128K | — |
| zenmux | $1.75 | $14.00 | $0.17 | — | 400K | 64K | — |
| anyapi | — | — | — | — | 400K | 128K | — |
| chatgpt · chatgpt | — | — | — | — | 128K | 64K | — |
| github_copilot · github-copilot | — | — | — | — | 128K | 64K | — |
| qiniu-ai | — | — | — | — | 400K | 128K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | nearai | Cache read | $0.18 |
| 2026-09-10 | nearai | Cache read | $0.175 |
| 2026-09-02 | nearai | Input | $1.80 |
| 2026-09-10 | nearai | Input | $1.75 |
| 2026-09-02 | nearai | Output | $15.50 |
| 2026-09-10 | nearai | Output | $14.00 |
Other listings of this model
same model, different key
More from OpenAI
most-hosted first