Cost-efficient GPT-5.6 model for fast, high-volume workloads
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
$0.20
Output
$1.20
Cache read
$0.02
Cache write
$0.25
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | openai | $0.10 |
| Batch output | openai | $0.60 |
| Priority input | azure | $0.40 |
| Priority input | azure | $0.44 |
| Priority output | azure | $2.40 |
| Priority output | azure | $2.64 |
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 | $0.04 |
| 272K | Cache write | $0.50 |
| 272K | Input | $0.40 |
| 272K | Output | $1.80 |
Quality
8 benchmarks · 2 sources
Composite
80th
percentile of 334 scored models
Rank
68 / 334
±0.08 sd
Evidence
8 × 2
3 or more benchmarks, from 2 or more sources
Effort range
19.0
points between effort settings
reasoning81st3/4 bench
math90th3/7 bench
knowledge49th1/1 bench
general34th1/1 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| max | 88th | 8 |
| low | 68th | 5 |
| medium | 32nd | 1 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| FrontierMath-Tier-4-v2 | 61.0 ±7.7 | max | Epoch AI | 2026-07-09 |
| GPQA diamond | 91.6 ±1.7 | max | Epoch AI | 2026-07-09 |
| ↳ | 82.3 ±2.7 | low | Epoch AI | 2026-08-07 |
| Settings differ by 9.3 points on this benchmark. | ||||
| Chess Puzzles | 40.0 ±4.9 | max | Epoch AI | 2026-07-09 |
| ↳ | 21.0 ±4.1 | low | Epoch AI | 2026-08-07 |
| Settings differ by 19.0 points on this benchmark. | ||||
| OTIS Mock AIME 2024-2025 | 98.3 ±1.2 | max | Epoch AI | 2026-07-09 |
| ↳ | 66.7 ±7.1 | low | Epoch AI | 2026-08-07 |
| Settings differ by 31.6 points on this benchmark. | ||||
| FrontierMath-Tiers-1-3-v2 | 82.1 ±2.3 | max | Epoch AI | 2026-07-09 |
| ↳ | 41.4 ±2.9 | low | Epoch AI | 2026-08-29 |
| Settings differ by 40.7 points on this benchmark. | ||||
| SimpleQA Verified | 41.0 ±1.6 | max | Epoch AI | 2026-08-10 |
| Mystery Game Puzzles | 21.0 ±4.1 | max | Epoch AI | 2026-07-28 |
| ↳ | 17.0 ±3.8 | low | Epoch AI | 2026-08-27 |
| ↳ | 12.0 ±3.3 | medium | Epoch AI | 2026-08-27 |
| Settings differ by 9.0 points on this benchmark. | ||||
| LiveBench | 73.7 | max · 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 45 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| openaivendor | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M 922K | 128K | — |
| kenari | free | free | — | — | 1.1M | 128K | — |
| bothub | $0.06 | $0.37 | — | — | 1.1M | 128K | — |
| 302ai | $0.20 | $1.20 | — | — | 1.1M | 128K | — |
| amazon-bedrock · global | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| azure | $0.20 $0.22 | $1.20 $1.32 | $0.02 $0.022 | $0.25 $0.275 | 1.1M 922K | 128K | 2028-01-11 |
| bedrock_converse · global | $0.20 | $1.20 | $0.02 | $0.25 | 1M | 128K | — |
| cloudflare-ai-gateway | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| crossmodel | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| edenai | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| github-copilot | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| impossibl | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| kilo | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| llmgateway | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| llmgateway-providers | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| merge-gateway | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| nano-gpt | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| neon | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| ofox | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| opencode | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| opencode-go | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| openrouter | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M 922K | 128K | — |
| opper | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| orcarouter | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| perplexity | $0.20 | $1.20 | $0.02 | — | — | — | — |
| requesty | $0.20 | $1.20 | $0.02 | — | 1.1M | 128K | — |
| vercel | $0.20 | $1.20 | $0.02 | $0.25 | 1.1M | 128K | — |
| cortecs | $0.219 | $1.32 | $0.022 | $0.275 | 1.1M | 128K | — |
| amazon-bedrock | $0.22 | $1.32 | $0.022 | $0.275 | 1.1M | 128K | — |
| amazon-bedrock · in | $0.22 | $1.32 | $0.022 | $0.275 | 1.1M | 128K | — |
| amazon-bedrock · us | $0.22 | $1.32 | $0.022 | $0.275 | 1.1M | 128K | — |
| bedrock_converse · us | $0.22 | $1.32 | $0.022 | $0.275 | 1M | 128K | — |
| bedrock_mantle · bedrock-mantle | $0.22 $0.264 | $1.32 $1.584 | $0.022 $0.0264 | $0.275 $0.33 | 1.1M | 128K | — |
| llmgateway-providers · aws-mantle | $0.22 | $1.32 | $0.022 | $0.275 | 279K | 128K | — |
| routing-run | $0.70 | $4.20 | — | — | 1M | 128K | — |
| abacus | $1.00 | $6.00 | $0.10 | — | 1M | 128K | — |
| ai-router | $1.00 | $6.00 | $0.10 | $1.25 | 1.1M | 128K | — |
| aihubmix | $1.00 | $6.00 | $0.10 | $1.25 | 1.1M | 128K | — |
| azure-cognitive-services | $1.00 | $6.00 | $0.10 | $1.25 | 1.1M | 128K | — |
| databricks | $1.00 | $6.00 | $0.10 | $1.25 | 400K 922K | 128K | — |
| pioneer | $1.00 | $6.00 | $0.10 | $1.25 | 1.1M | 128K | — |
| sap-ai-core | $1.00 | $6.00 | $0.10 | — | 1.1M | 128K | — |
| vivgrid | $1.00 | $6.00 | $0.10 | $1.25 | 1.1M | 128K | — |
| zenmux | $1.00 | $6.00 | $0.10 | $1.25 | 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 | bedrock_mantle · bedrock-mantle | Cache read | $0.022 |
| 2026-09-04 | bedrock_mantle · bedrock-mantle | Cache read | $0.022 |
| 2026-09-02 | databricks | Cache read | $0.10 |
| 2026-09-06 | databricks | Cache read | $0.10 |
| 2026-09-02 | neon | Cache read | $0.10 |
| 2026-09-02 | neon | Cache read | $0.02 |
| 2026-09-02 | openrouter | Cache read | $0.02 |
| 2026-09-06 | openrouter | Cache read | $0.02 |
| 2026-09-02 | bedrock_mantle · bedrock-mantle | Cache write | $0.275 |
| 2026-09-04 | bedrock_mantle · bedrock-mantle | Cache write | $0.275 |
| 2026-09-02 | bedrock_mantle · bedrock-mantle | Input | $0.22 |
| 2026-09-04 | bedrock_mantle · bedrock-mantle | Input | $0.22 |
| 2026-09-02 | databricks | Input | $1.00 |
| 2026-09-06 | databricks | Input | $1.00 |
| 2026-09-02 | neon | Input | $1.00 |
| 2026-09-02 | neon | Input | $0.20 |
| 2026-09-02 | openrouter | Input | $0.20 |
| 2026-09-06 | openrouter | Input | $0.20 |
| 2026-09-02 | bedrock_mantle · bedrock-mantle | Output | $1.32 |
| 2026-09-04 | bedrock_mantle · bedrock-mantle | Output | $1.32 |
| 2026-09-02 | databricks | Output | $6.00 |
| 2026-09-06 | databricks | Output | $6.00 |
| 2026-09-02 | neon | Output | $6.00 |
| 2026-09-02 | neon | Output | $1.20 |
| 2026-09-02 | openrouter | Output | $1.20 |
| 2026-09-06 | openrouter | Output | $1.20 |
Other listings of this model
same model, different key
More from OpenAI
most-hosted first