Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs
Specification
openai listing
Context
400K
Max output
128K
Released
2025-08-07
Knowledge cutoff
2024-05-30
Retires
2026-12-11
Open weights
no
Input
text, image
Output
text
Price
US dollars per million tokens · openai list price
Input
$0.05
Output
$0.40
Cache read
$0.005
Cache write
$0.05
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | openai | $0.025 |
| Batch output | openai | $0.20 |
| Priority input | openai | $2.50 |
Batch input is 50% below the interactive input price at the same listing.
Quality
11 benchmarks · 2 sources
Composite
40th
percentile of 334 scored models
Rank
202 / 334
±0.05 sd
Evidence
11 × 2
3 or more benchmarks, from 2 or more sources
Effort range
10.8
points between effort settings
coding19th1/3 bench
reasoning49th3/4 bench
math44th6/7 bench
knowledge6th1/1 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| medium | 52nd | 7 |
| high | 46th | 10 |
| low | 26th | 5 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| MATH level 5 | 95.2 ±0.5 | medium | Epoch AI | 2025-08-20 |
| ↳ | 94.9 ±0.5 | high | Epoch AI | 2025-08-20 |
| Settings differ by 0.3 points on this benchmark. | ||||
| OTIS Mock AIME 2024-2025 | 81.1 ±4.6 | high | Epoch AI | 2025-10-31 |
| ↳ | 74.2 ±5.2 | medium | Epoch AI | 2025-08-07 |
| ↳ | 41.1 ±7.5 | low · 2 runs | Epoch AI | 2026-07-13 |
| Settings differ by 40.0 points on this benchmark. | ||||
| GPQA diamond | 69.4 ±2.8 | high | Epoch AI | 2025-10-30 |
| ↳ | 67.4 ±2.7 | medium | Epoch AI | 2025-08-07 |
| ↳ | 53.0 ±3.5 | low · 2 runs | Epoch AI | 2026-07-13 |
| Settings differ by 16.4 points on this benchmark. | ||||
| Chess Puzzles | 27.0 ±4.5 | high | Epoch AI | 2026-08-07 |
| ↳ | 8.0 ±3.6 | low · 2 runs | Epoch AI | 2026-07-13 |
| Settings differ by 19.0 points on this benchmark. | ||||
| FrontierMath-v1 | 14.1 ±13.3 | high · 2 runs | Epoch AI | 2025-10-30 |
| ↳ | 8.6 ±10.0 | medium · 2 runs | Epoch AI | 2025-08-07 |
| Settings differ by 5.5 points on this benchmark. | ||||
| FrontierMath-Tier-4-2025-07-01 | 1.0 ±2.1 | medium · 2 runs | Epoch AI | 2025-08-07 |
| ↳ | 0.0 ±0.0 | high · 2 runs | Epoch AI | 2025-10-30 |
| Settings differ by 1.0 points on this benchmark. | ||||
| Mystery Game Puzzles | 9.0 ±2.9 | medium | Epoch AI | 2026-08-27 |
| ↳ | 8.0 ±2.7 | high | Epoch AI | 2026-08-27 |
| ↳ | 7.0 ±2.9 | low · 2 runs | Epoch AI | 2026-08-27 |
| Settings differ by 2.0 points on this benchmark. | ||||
| SWE-Bench verified | 34.8 | medium · mini-SWE-agent | SWE-bench | — |
| FrontierMath-Tier-4-v2 | 2.4 ±2.4 | high | Epoch AI | 2026-06-12 |
| FrontierMath-Tiers-1-3-v2 | 20.0 ±2.4 | high | Epoch AI | 2026-06-12 |
| ↳ | 3.9 ±0.8 | low · 2 runs | Epoch AI | 2026-08-27 |
| Settings differ by 16.1 points on this benchmark. | ||||
| SimpleQA Verified | 11.7 ±1.0 | 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 29 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| openaivendor | $0.05 | $0.40 | $0.005 | — | 400K 272K | 128K | 2026-12-11 |
| jiekou | $0.045 | $0.36 | — | — | 400K | 128K | — |
| poe | $0.045 | $0.36 | $0.0045 | — | 400K | 128K | — |
| abacus | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| azure | $0.05 $0.055 | $0.40 $0.44 | $0.01 $0.0055 $0.005 | — | 400K 272K | 128K | 2027-02-09 |
| azure-cognitive-services | $0.05 | $0.40 | $0.01 | — | 400K | 128K | — |
| cloudflare-ai-gateway | $0.05 | $0.40 | $0.005 | — | 128K | 128K | — |
| databricks | $0.05 | $0.40 | $0.005 | $0.05 | 400K 272K | 128K | — |
| edenai | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| fastrouter | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| helicone | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| impossibl | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| kilo | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| llmgateway | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| llmgateway-providers | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| merge-gateway | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| nano-gpt | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| nearai | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| neon | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| oci · oci | $0.05 | $0.40 | — | — | 272K | 128K | — |
| ofox | $0.05 | $0.40 | $0.01 | — | 400K | 128K | — |
| opencode | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| openrouter | $0.05 | $0.40 | $0.005 | — | 400K 272K | 128K | — |
| orcarouter | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| pioneer | $0.05 | $0.40 | $0.005 | $0.05 | 400K | 128K | — |
| replicate · replicate | $0.05 | $0.40 | — | — | — | — | — |
| sap-ai-core | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| vercel | $0.05 | $0.40 | $0.005 | — | 400K | 128K | — |
| cortecs | $0.06 | $0.439 | $0.019 | — | 400K | 128K | — |
More from OpenAI
most-hosted first