Strong small GPT for coding subagents, quick tool use, and high-volume work
Specification
openai listing
Context
400K
Max output
128K
Released
2026-03-17
Knowledge cutoff
2025-08-31
Retires
2027-09-21
Open weights
no
Input
text, image
Output
text
Price
US dollars per million tokens · openai list price
Input
$0.75
Output
$4.50
Cache read
$0.075
Cache write
$0.75
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | openai | $0.375 |
| Batch output | openai | $2.25 |
| Priority input | azure_ai | $1.50 |
| Priority output | azure_ai | $9.00 |
Batch input is 50% below the interactive input price at the same listing.
Quality
10 benchmarks · 2 sources
Composite
50th
percentile of 334 scored models
Rank
169 / 334
±0.07 sd
Evidence
10 × 2
3 or more benchmarks, from 2 or more sources
Effort range
3.3
points between effort settings
reasoning67th3/4 bench
math58th5/7 bench
knowledge24th1/1 bench
general7th1/1 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| high | 69th | 6 |
| xhigh | 63rd | 6 |
| low | 25th | 2 |
| medium | 18th | 1 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9 ±4.7 | xhigh | Epoch AI | 2026-08-07 |
| ↳ | 87.2 ±4.3 | high | Epoch AI | 2026-04-15 |
| Settings differ by 1.7 points on this benchmark. | ||||
| GPQA diamond | 86.9 ±2.4 | xhigh | Epoch AI | 2026-08-07 |
| ↳ | 83.6 ±2.2 | high | Epoch AI | 2026-04-15 |
| Settings differ by 3.3 points on this benchmark. | ||||
| FrontierMath-v1 | 39.1 ±16.7 | high · 2 runs | Epoch AI | 2026-04-15 |
| Chess Puzzles | 24.0 ±4.3 | xhigh | Epoch AI | 2026-08-07 |
| ↳ | 18.0 ±3.9 | high | Epoch AI | 2026-04-15 |
| Settings differ by 6.0 points on this benchmark. | ||||
| FrontierMath-Tiers-1-3-v2 | 51.2 ±3.0 | xhigh | Epoch AI | 2026-06-12 |
| ↳ | 24.6 ±2.6 | low | Epoch AI | 2026-08-28 |
| Settings differ by 26.6 points on this benchmark. | ||||
| FrontierMath-Tier-4-2025-07-01 | 2.1 ±2.1 | high | Epoch AI | 2026-04-15 |
| SimpleQA Verified | 29.4 ±1.4 | high | Epoch AI | 2026-08-27 |
| FrontierMath-Tier-4-v2 | 9.8 ±4.7 | xhigh | Epoch AI | 2026-06-12 |
| Mystery Game Puzzles | 8.0 ±2.7 | low | Epoch AI | 2026-08-27 |
| ↳ | 7.0 ±2.6 | medium | Epoch AI | 2026-08-27 |
| Settings differ by 1.0 points on this benchmark. | ||||
| LiveBench | 66.6 | xhigh · 23 runs | LiveBench | 2026-06-25 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 38 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| openaivendor | $0.75 | $4.50 | $0.075 | — | 400K 272K | 128K | — |
| kenari | free | free | — | — | 400K | 128K | — |
| xpersona | $0.375 | $4.00 | $0.0375 | — | 272K | 128K | — |
| poe | $0.68 | $4.00 | $0.068 | — | 400K | 128K | — |
| 302ai | $0.75 | $4.50 | — | — | 400K | 128K | — |
| abacus | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| aihubmix | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| azure | $0.75 | $4.50 | $0.075 | — | 400K 272K | 128K | 2027-09-21 |
| azure_ai | $0.75 | $4.50 | $0.075 | — | 272K | 128K | 2027-09-21 |
| azure-cognitive-services | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| cloudflare-ai-gateway | $0.75 | $4.50 | $0.075 | — | 128K | 128K | — |
| crossmodel | $0.75 | $4.50 | $0.075 | $0.75 | 400K | 128K | — |
| databricks | $0.75 | $4.50 | $0.075 | $0.75 | 400K 272K | 128K | — |
| edenai | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| fastrouter | $0.75 | $4.50 | — | — | 400K | 128K | — |
| freemodel | $0.75 | $4.50 | $0.075 | $0.75 | 400K | 128K | — |
| frogbot | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| github-copilot | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| impossibl | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| kilo | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| llmgateway | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| llmgateway-providers | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| merge-gateway | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| nano-gpt | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| nearai | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| neon | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| ofox | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| opencode | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| openrouter | $0.75 | $4.50 | $0.075 | — | 400K 272K | 128K | — |
| opper | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| orcarouter | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| perplexity | $0.75 | $4.50 | $0.075 | — | — | — | — |
| pioneer | $0.75 | $4.50 | $0.075 | $0.75 | 400K | 128K | — |
| requesty | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| vercel | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| vivgrid | $0.75 | $4.50 | $0.075 | — | 400K | 128K | — |
| zenmux | $0.75 | $4.50 | — | — | 400K | 128K | — |
| model-oracle-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 | openrouter | Cache read | $0.075 |
| 2026-09-06 | openrouter | Cache read | $0.075 |
| 2026-09-02 | openrouter | Input | $0.75 |
| 2026-09-06 | openrouter | Input | $0.75 |
| 2026-09-02 | openrouter | Output | $4.50 |
| 2026-09-06 | openrouter | Output | $4.50 |
Other listings of this model
same model, different key
More from OpenAI
most-hosted first