Deliberate o-series reasoner for hard math, coding, and multi-step analysis
Specification
openai listing
Context
200K
Max output
100K
Released
2025-04-16
Knowledge cutoff
2024-05
Retires
2026-12-11
Open weights
no
Input
text, image, pdf
Output
text
Price
US dollars per million tokens · openai list price
Input
$2.00
Output
$8.00
Cache read
$0.50
Cache write
free
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | azure | $1.00 |
| Batch input | azure | $1.10 |
| Batch output | azure | $4.00 |
| Batch output | azure | $4.40 |
| Priority input | openai | $3.50 |
| Priority output | openai | $14.00 |
Batch input is 50% below the interactive input price at the same listing.
Quality
11 benchmarks · 3 sources
Composite
70th
percentile of 344 scored models
Rank
104 / 344
±0.04 sd
Evidence
11 × 3
3 or more benchmarks, from 2 or more sources
Effort range
4.2
points between effort settings
coding72nd2/3 bench
reasoning74th3/4 bench
math60th5/7 bench
knowledge67th1/1 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| MATH level 5 | 97.8 ±0.3 | default | Epoch AI | 2025-04-16 |
| Aider polyglot | 81.3 | high · aider diff | Aider | 2025-06-25 |
| ↳ | 76.9 | default · aider diff | Aider | 2025-06-25 |
| Settings differ by 4.4 points on this benchmark. | ||||
| GPQA diamond | 80.8 ±2.8 | default · 3 runs | Epoch AI | 2026-08-07 |
| OTIS Mock AIME 2024-2025 | 76.1 ±5.5 | default · 3 runs | Epoch AI | 2026-08-07 |
| SimpleQA Verified | 49.4 ±1.6 | default | Epoch AI | 2026-08-27 |
| Chess Puzzles | 36.3 ±4.8 | default · 3 runs | Epoch AI | 2026-10-13 |
| SWE-Bench verified | 62.3 ±2.2 | default | Epoch AI | 2026-02-12 |
| ↳ | 58.4 | default · mini-SWE-agent | SWE-bench | — |
| Sources and settings disagree by 3.9 points. Both figures stand. | ||||
| Mystery Game Puzzles | 26.0 ±4.6 | default · 2 runs | Epoch AI | 2026-08-27 |
| FrontierMath-v1 | 10.9 ±1.7 | default · 6 runs | Epoch AI | 2025-11-17 |
| FrontierMath-Tier-4-2025-07-01 | 1.0 ±2.1 | default · 2 runs | Epoch AI | 2025-07-01 |
| FrontierMath-Tiers-1-3-v2 | 27.5 ±2.8 | default · 3 runs | Epoch AI | 2026-08-27 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 23 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| openaivendor | $2.00 | $8.00 | $0.50 | — | 200K | 100K | 2026-12-11 |
| poe | $1.8182 | $7.2727 | $0.4545 | — | 200K | 100K | — |
| 302ai | $2.00 | $8.00 | — | — | 200K | 100K | — |
| abacus | $2.00 | $8.00 | $0.50 | — | 200K | 100K | — |
| aihubmix | $2.00 | $8.00 | $0.50 | — | 200K | 100K | — |
| azure | $2.00 $2.20 | $8.00 $8.80 | $0.50 $0.55 | — | 200K | 100K | 2026-11-19 |
| azure-cognitive-services | $2.00 | $8.00 | $0.50 | — | 200K | 100K | — |
| cloudflare-ai-gateway | $2.00 | $8.00 | $0.50 | — | 200K | 100K | — |
| edenai | $2.00 | $8.00 | $0.50 | — | 200K | 100K | — |
| helicone | $2.00 | $8.00 | $0.50 | — | 200K | 100K | — |
| impossibl | $2.00 | $8.00 | $0.50 | — | 200K | 100K | — |
| kilo | $2.00 | $8.00 | $0.50 | — | 200K | 100K | — |
| llmgateway | $2.00 | $8.00 | $0.50 | — | 200K | 100K | — |
| llmgateway-providers | $2.00 | $8.00 | $0.50 | — | 200K | 100K | — |
| lowrouter · auto | $2.00 | $8.00 | $0.50 | — | 200K | 100K | — |
| merge-gateway | $2.00 | $8.00 | $0.50 | — | 200K | 100K | — |
| nano-gpt | $2.00 | $8.00 | $1.00 | — | 200K | 100K | — |
| nearai | $2.00 | $8.00 | $0.50 | — | 200K | 100K | — |
| openrouter | $2.00 | $8.00 | $0.50 | — | 200K | 100K | — |
| vercel | $2.00 | $8.00 | $0.50 | — | 200K | 100K | — |
| vercel_ai_gateway · vercel-ai-gateway | $2.00 | $8.00 | $0.50 | free | 200K | 100K | — |
| jiekou | $9.50 | $38.00 | $0.475 | — | 200K | 100K | — |
| anyapi | — | — | — | — | 200K | 100K | — |
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 | $0.50 |
| 2026-09-06 | openrouter | Cache read | $0.50 |
| 2026-10-10 | openrouter | Cache read | $0.50 |
| 2026-09-02 | poe | Cache read | $0.45 |
| 2026-10-22 | poe | Cache read | $0.4545 |
| 2026-09-02 | jiekou | Input | $10.00 |
| 2026-10-22 | jiekou | Input | $9.50 |
| 2026-09-02 | openrouter | Input | $2.00 |
| 2026-09-06 | openrouter | Input | $2.00 |
| 2026-10-10 | openrouter | Input | $2.00 |
| 2026-09-02 | poe | Input | $1.80 |
| 2026-10-22 | poe | Input | $1.8182 |
| 2026-09-02 | jiekou | Output | $40.00 |
| 2026-10-22 | jiekou | Output | $38.00 |
| 2026-09-02 | openrouter | Output | $8.00 |
| 2026-09-06 | openrouter | Output | $8.00 |
| 2026-10-10 | openrouter | Output | $8.00 |
| 2026-09-02 | poe | Output | $7.20 |
| 2026-10-22 | poe | Output | $7.2727 |
More from OpenAI
most-hosted first