Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows
Specification
openai listing
Context
1.1M
Max output
128K
Released
2026-07-09
Knowledge cutoff
2026-02-16
Retires
2028-01-11
Open weights
no
Input
text, image, pdf
Output
text
Price
US dollars per million tokens · openai list price
Input
$4.00
Output
$20.00
Cache read
$0.40
Cache write
$5.00
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | openai | $2.00 |
| Batch output | openai | $10.00 |
| Priority input | azure | $10.00 |
| Priority input | azure | $11.00 |
| Priority input | openai | $8.00 |
| Priority output | azure | $60.00 |
| Priority output | azure | $66.00 |
| Priority output | openai | $40.00 |
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 | $1.00 |
| 272K | Cache write | $12.50 |
| 272K | Input | $10.00 |
| 272K | Output | $45.00 |
Quality
12 benchmarks · 2 sources
Composite
94th
percentile of 334 scored models
Rank
20 / 334
±0.07 sd
Evidence
12 × 2
3 or more benchmarks, from 2 or more sources
Effort range
16.2
points between effort settings
coding27th1/3 bench
reasoning95th4/4 bench
math97th4/7 bench
knowledge94th1/1 bench
general93rd1/1 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| max | 98th | 9 |
| medium | 88th | 1 |
| low | 88th | 4 |
| high | 32nd | 1 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| FrontierMath-Tier-4-v2 | 82.9 ±5.9 | max | Epoch AI | 2026-07-09 |
| FrontierMath-Tiers-1-3-v2 | 89.1 ±1.8 | max | Epoch AI | 2026-07-09 |
| Chess Puzzles | 55.0 ±5.0 | max | Epoch AI | 2026-07-09 |
| ↳ | 27.0 ±4.5 | low | Epoch AI | 2026-08-07 |
| Settings differ by 28.0 points on this benchmark. | ||||
| SimpleQA Verified | 69.7 ±1.5 | max | Epoch AI | 2026-08-10 |
| Mystery Game Puzzles | 58.0 ±5.0 | max | Epoch AI | 2026-07-28 |
| ↳ | 26.0 ±4.4 | low | Epoch AI | 2026-08-27 |
| Settings differ by 32.0 points on this benchmark. | ||||
| OTIS Mock AIME 2024-2025 | 100.0 ±0.0 | max | Epoch AI | 2026-07-09 |
| ↳ | 95.6 ±3.1 | low | Epoch AI | 2026-08-07 |
| Settings differ by 4.4 points on this benchmark. | ||||
| LiveBench | 81.6 | max · 23 runs | LiveBench | 2026-06-25 |
| GPQA diamond | 93.5 ±1.6 | max | Epoch AI | 2026-07-09 |
| ↳ | 89.9 ±2.1 | low | Epoch AI | 2026-08-07 |
| Settings differ by 3.6 points on this benchmark. | ||||
| EBR-bench | 44.8 ±4.2 | max | Epoch AI | 2026-09-04 |
| OEIS Open Lite | 43.0 ±5.0 | medium | Epoch AI | 2026-08-11 |
| FrontierMath-Erdos | 0.0 ±0.0 | max | Epoch AI | 2026-08-28 |
| MirrorCode | 20.0 ±9.2 | 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 45 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| openaivendor | $4.00 | $20.00 | $0.40 | $5.00 | 1.1M 922K | 128K | — |
| kenari | free | free | — | — | 1.1M | 128K | — |
| xpersona | $1.50 | $12.00 | $0.15 | — | 372K | 128K | — |
| cloudflare-ai-gateway | $2.00 | $10.00 | $0.25 | $3.125 | 1.1M | 128K | — |
| nano-gpt | $2.00 | $10.00 | $0.20 | $2.50 | 1.1M | 128K | — |
| opencode | $2.00 | $10.00 | $0.20 | $2.50 | 1.1M | 128K | — |
| openrouter | $2.00 | $10.00 | $0.20 | $2.50 | 1.1M | 128K | — |
| vercel | $2.00 | $10.00 | $0.20 | $2.50 | 1.1M | 128K | — |
| infer · official | $2.50 | $12.50 | $0.25 | $3.125 | 272K | 128K | — |
| ofox | $2.50 | $15.00 | $0.25 | $3.125 | 1.1M | 128K | — |
| routing-run | $2.50 | $15.00 | — | — | 1M | 128K | — |
| amazon-bedrock · global | $4.00 | $20.00 | $0.40 | $5.00 | 1.1M | 128K | — |
| azure | $4.00 $5.00 $5.50 | $20.00 $30.00 $33.00 | $0.50 $0.55 | $6.25 $6.875 | 1.1M 922K | 128K | 2028-01-11 |
| bedrock_converse · global | $4.00 | $20.00 | $0.40 | $5.00 | 1M | 128K | — |
| crossmodel | $4.00 | $20.00 | $0.40 | $5.00 | 1.1M | 128K | — |
| edenai | $4.00 | $20.00 | $0.40 | $5.00 | 1.1M | 128K | — |
| github-copilot | $4.00 | $20.00 | $0.40 | $5.00 | 1.1M | 128K | — |
| kilo | $4.00 | $20.00 | $0.40 | $5.00 | 1.1M | 128K | — |
| orcarouter | $4.00 | $20.00 | $0.40 | $5.00 | 1.1M | 128K | — |
| requesty | $4.00 | $20.00 | $0.40 | $5.00 | 1.1M | 128K | — |
| amazon-bedrock | $4.40 | $22.00 | $0.44 | $5.50 | 1.1M | 128K | — |
| amazon-bedrock · us | $4.40 | $22.00 | $0.44 | $5.50 | 1.1M | 128K | — |
| bedrock_converse · us | $4.40 | $22.00 | $0.44 | $5.50 | 1M | 128K | — |
| 302ai | $5.00 | $30.00 | — | — | 1.1M | 128K | — |
| abacus | $5.00 | $30.00 | $0.50 | — | 1M | 128K | — |
| ai-router | $5.00 | $30.00 | $0.50 | $6.25 | 1.1M | 128K | — |
| aihubmix | $5.00 | $30.00 | $0.50 | $6.25 | 1.1M | 128K | — |
| azure-cognitive-services | $5.00 | $30.00 | $0.50 | — | 1.1M | 128K | — |
| databricks | $5.00 $4.00 | $30.00 $20.00 | $0.50 $0.40 | $5.00 | 1.1M 922K | 128K | — |
| impossibl | $5.00 | $30.00 | $0.50 | $6.25 | 1.1M | 128K | — |
| llmgateway | $5.00 | $30.00 | $0.50 | $6.25 | 1.1M | 128K | — |
| llmgateway-providers | $5.00 | $30.00 | $0.50 | $6.25 | 1.1M | 128K | — |
| merge-gateway | $5.00 | $30.00 | $0.50 | $5.00 | 1.1M | 128K | — |
| neon | $5.00 | $30.00 | $0.50 | $6.25 | 1.1M | 128K | — |
| opper | $5.00 | $30.00 | $0.50 | $6.25 | 1.1M | 128K | — |
| perplexity | $5.00 | $30.00 | $0.50 | — | — | — | — |
| pioneer | $5.00 | $30.00 | $0.50 | $6.25 | 1.1M | 128K | — |
| sap-ai-core | $5.00 | $30.00 | $0.50 | — | 1.1M | 128K | — |
| vivgrid | $5.00 | $30.00 | $0.50 | $6.25 | 1.1M | 128K | — |
| zenmux | $5.00 | $30.00 | $0.50 | $6.25 | 1.1M | 128K | — |
| bedrock_mantle · bedrock-mantle | $5.50 | $33.00 | $0.55 | $6.875 | 1.1M | 128K | — |
| cortecs | $5.50 | $32.998 | $0.55 | $6.879 | 1.1M | 128K | — |
| llmgateway-providers · aws-mantle | $5.50 | $33.00 | $0.55 | $6.875 | 279K | 128K | — |
| agentrouter | — | — | — | — | 1.1M | 128K | — |
| chatgpt · chatgpt | — | — | — | — | 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 | crossmodel | Cache read | $0.50 |
| 2026-09-06 | crossmodel | Cache read | $0.40 |
| 2026-09-02 | databricks | Cache read | $0.50 |
| 2026-09-06 | databricks | Cache read | $0.50 |
| 2026-09-02 | github-copilot | Cache read | $0.20 |
| 2026-09-05 | github-copilot | Cache read | $0.40 |
| 2026-09-02 | openrouter | Cache read | $0.20 |
| 2026-09-11 | openrouter | Cache read | $0.20 |
| 2026-09-02 | crossmodel | Cache write | $6.25 |
| 2026-09-06 | crossmodel | Cache write | $5.00 |
| 2026-09-02 | github-copilot | Cache write | $2.50 |
| 2026-09-05 | github-copilot | Cache write | $5.00 |
| 2026-09-02 | openrouter | Cache write | $2.50 |
| 2026-09-11 | openrouter | Cache write | $2.50 |
| 2026-09-02 | azure | Input | $5.00 |
| 2026-09-03 | azure | Input | $4.00 |
| 2026-09-02 | crossmodel | Input | $5.00 |
| 2026-09-06 | crossmodel | Input | $4.00 |
| 2026-09-02 | databricks | Input | $5.00 |
| 2026-09-06 | databricks | Input | $5.00 |
| 2026-09-02 | github-copilot | Input | $2.00 |
| 2026-09-05 | github-copilot | Input | $4.00 |
| 2026-09-02 | openrouter | Input | $2.00 |
| 2026-09-11 | openrouter | Input | $2.00 |
| 2026-09-02 | azure | Output | $30.00 |
| 2026-09-03 | azure | Output | $20.00 |
| 2026-09-02 | crossmodel | Output | $30.00 |
| 2026-09-06 | crossmodel | Output | $20.00 |
| 2026-09-02 | databricks | Output | $30.00 |
| 2026-09-06 | databricks | Output | $30.00 |
| 2026-09-02 | github-copilot | Output | $10.00 |
| 2026-09-05 | github-copilot | Output | $20.00 |
| 2026-09-02 | openrouter | Output | $10.00 |
| 2026-09-11 | openrouter | Output | $10.00 |
Other listings of this model
same model, different key
More from OpenAI
most-hosted first