Agent-ready GPT for coding and computer-use workflows at a lower cost
Specification
openai listing
Context
1.1M
Max output
128K
Released
2026-03-05
Knowledge cutoff
2025-08-31
Retires
2027-09-02
Open weights
no
Input
text, image, pdf
Output
text
Price
US dollars per million tokens · openai list price
Input
$2.50
Output
$15.00
Cache read
$0.25
Cache write
$2.50
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | openai | $1.25 |
| Batch output | openai | $7.50 |
| Priority input | azure_ai | $5.00 |
| Priority input | azure | $5.50 |
| Priority output | azure_ai | $30.00 |
| Priority output | azure | $33.00 |
Batch input is 50% below the interactive input price at the same listing.
Long-context price tiers
the rate above each context threshold
| Above | Price | $/M |
|---|---|---|
| 272K | Cache read | $0.50 |
| 272K | Input | $5.00 |
| 272K | Output | $22.50 |
Quality
13 benchmarks · 2 sources
Composite
88th
percentile of 334 scored models
Rank
41 / 334
±0.06 sd
Evidence
13 × 2
3 or more benchmarks, from 2 or more sources
Effort range
16.7
points between effort settings
coding49th2/3 bench
reasoning87th4/4 bench
math95th5/7 bench
knowledge55th1/1 bench
general75th1/1 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| high | 96th | 7 |
| medium | 93rd | 4 |
| xhigh | 92nd | 11 |
| low | 77th | 4 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| FrontierMath-Tier-4-2025-07-01 | 50.0 ±50.0 | high | Epoch AI | 2026-04-02 |
| ↳ | 38.5 ±50.0 | xhigh · 2 runs | Epoch AI | 2026-04-02 |
| Settings differ by 11.5 points on this benchmark. | ||||
| FrontierMath-v1 | 80.0 ±13.3 | high | Epoch AI | 2026-04-02 |
| ↳ | 47.6 ±2.9 | xhigh | Epoch AI | 2026-03-06 |
| Settings differ by 32.4 points on this benchmark. | ||||
| Chess Puzzles | 44.0 ±5.0 | xhigh | Epoch AI | 2026-03-11 |
| ↳ | 38.0 ±4.9 | high | Epoch AI | 2026-07-15 |
| ↳ | 38.0 ±4.9 | medium | Epoch AI | 2026-07-15 |
| ↳ | 20.0 ±4.0 | low | Epoch AI | 2026-07-15 |
| Settings differ by 24.0 points on this benchmark. | ||||
| FrontierMath-Tiers-1-3-v2 | 78.6 ±2.4 | xhigh | Epoch AI | 2026-06-11 |
| OTIS Mock AIME 2024-2025 | 97.8 ±2.2 | high | Epoch AI | 2026-07-15 |
| ↳ | 95.6 ±3.1 | medium | Epoch AI | 2026-07-15 |
| ↳ | 95.3 ±3.2 | xhigh | Epoch AI | 2026-03-06 |
| ↳ | 84.4 ±5.5 | low | Epoch AI | 2026-07-15 |
| Settings differ by 13.4 points on this benchmark. | ||||
| GPQA diamond | 93.3 ±1.8 | xhigh | Epoch AI | 2026-03-06 |
| ↳ | 89.9 ±2.1 | high | Epoch AI | 2026-07-15 |
| ↳ | 88.9 ±2.2 | medium | Epoch AI | 2026-07-15 |
| ↳ | 84.8 ±2.6 | low | Epoch AI | 2026-07-15 |
| Settings differ by 8.5 points on this benchmark. | ||||
| SWE-Bench verified | 76.9 ±1.9 | high | Epoch AI | 2026-03-06 |
| LiveBench | 78.8 | xhigh · 23 runs | LiveBench | 2026-06-25 |
| FrontierMath-Tier-4-v2 | 49.0 ±8.0 | xhigh | Epoch AI | 2026-06-11 |
| Mystery Game Puzzles | 37.0 ±4.9 | xhigh | Epoch AI | 2026-07-24 |
| ↳ | 28.0 ±4.5 | medium | Epoch AI | 2026-08-28 |
| ↳ | 17.0 ±3.8 | low | Epoch AI | 2026-08-27 |
| Settings differ by 20.0 points on this benchmark. | ||||
| SimpleQA Verified | 45.1 ±1.6 | xhigh | Epoch AI | 2026-08-27 |
| EBR-bench | 25.4 | xhigh | Epoch AI | 2026-06-25 |
| MirrorCode | 15.6 ±7.7 | high | Epoch AI | 2026-08-10 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 46 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| openaivendor | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| unorouter · free | free | free | — | — | 1.1M | 128K | — |
| xpersona | $0.75 | $6.00 | $0.075 | — | 1.1M | 128K | — |
| unorouter | $1.80 | $10.80 | — | — | 1.1M | 128K | — |
| poe | $2.20 | $14.00 | $0.22 | — | 1.1M | 128K | — |
| 302ai | $2.50 | $15.00 | $0.25 | free | 1.1M | 128K | — |
| abacus | $2.50 | $15.00 | $0.25 | — | 400K | 128K | — |
| ai-router | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| aihubmix | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| azure | $2.50 $2.75 | $15.00 $16.50 | $0.25 $0.28 | — | 1.1M | 128K | 2027-09-02 |
| azure_ai | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | 2027-09-02 |
| azure-cognitive-services | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| cloudflare-ai-gateway | $2.50 | $15.00 | $0.25 | — | 1M | 128K | — |
| crossmodel | $2.50 | $15.00 | $0.25 | $2.50 | 1.1M | 128K | — |
| daoxe | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| databricks | $2.50 | $15.00 | $0.25 | $2.50 | 1.1M 922K | 128K | — |
| edenai | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| freemodel | $2.50 | $15.00 | $0.25 | $2.50 | 1.1M | 128K | — |
| github-copilot | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| impossibl | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| kilo | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| llmgateway | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| llmgateway-providers | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| merge-gateway | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| nano-gpt | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| nearai | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| neon | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| ofox | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| opencode | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| openrouter | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| opper | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| orcarouter | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| perplexity | $2.50 | $15.00 | $0.25 | — | — | — | — |
| perplexity-agent | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| pioneer | $2.50 | $15.00 | $0.25 | $2.50 | 1.1M | 128K | — |
| sap-ai-core | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| vercel | $2.50 | $15.00 | $0.25 | — | 1.1M | 128K | — |
| vivgrid | $2.50 | $15.00 | $0.25 | — | 400K | 128K | — |
| amazon-bedrock | $2.75 | $16.50 | $0.275 | — | 272K | 128K | — |
| bedrock_mantle · bedrock-mantle | $2.75 $3.30 | $16.50 $19.80 | $0.275 $0.33 | — | 1.1M | 128K | — |
| requesty | $2.75 | $16.50 | $0.275 | — | 1.1M | 128K | — |
| cortecs | $2.898 | $15.453 | $0.242 | — | 1.1M | 128K | — |
| zenmux | $3.75 | $18.75 | — | — | 1.1M | 128K | — |
| anyapi | — | — | — | — | 1.1M | 128K | — |
| chatgpt · chatgpt | — | — | — | — | 1.1M | 128K | — |
| model-oracle-ai | — | — | — | — | 1.1M | 128K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | bedrock_mantle · bedrock-mantle | Cache read | $0.275 |
| 2026-09-04 | bedrock_mantle · bedrock-mantle | Cache read | $0.275 |
| 2026-09-02 | openrouter | Cache read | $0.25 |
| 2026-09-06 | openrouter | Cache read | $0.25 |
| 2026-09-02 | bedrock_mantle · bedrock-mantle | Input | $2.75 |
| 2026-09-04 | bedrock_mantle · bedrock-mantle | Input | $2.75 |
| 2026-09-02 | openrouter | Input | $2.50 |
| 2026-09-06 | openrouter | Input | $2.50 |
| 2026-09-02 | bedrock_mantle · bedrock-mantle | Output | $16.50 |
| 2026-09-04 | bedrock_mantle · bedrock-mantle | Output | $16.50 |
| 2026-09-02 | openrouter | Output | $15.00 |
| 2026-09-06 | openrouter | Output | $15.00 |
Other listings of this model
same model, different key
More from OpenAI
most-hosted first