GPT-5.1
GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5.
text + image + file → text · made by OpenAI
$1.25→$10per Mtok in / out
OpenAI · 7 sellers
Sold by 24 ways
| Seller | Lane | Rate |
|---|---|---|
| Microsoft Azure AI cloud | batch | $0.62per Mtok in$5per Mtok out$0.062per Mtok cachedprices.azure.com · read 2026-08-24 |
| Databricks cloud | standard | $1.25per Mtok in$10per Mtok out$0.12per Mtok cached$1.25per Mtok cache writemodels.dev · read 2026-09-16 |
| Microsoft Azure AI cloud | standard | $1.25per Mtok in$10per Mtok out$0.12per Mtok cachedmodels.dev · read 2026-09-16 |
| OpenAI api | standard | $1.25per Mtok in$10per Mtok out$0.12per Mtok cacheddevelopers.openai.com · read 2026-08-24 |
| Microsoft Azure AI cloud | priority | $2.5per Mtok in$20per Mtok out$0.25per Mtok cachedraw.githubusercontent.com · read 2026-09-16 |
| Requesty 3 ways | $0.56per Mtok in$4.5per Mtok out$0.056per Mtok cached | |
| Requesty aggregatornot on the seller's list today | openai flex | $0.56per Mtok in$4.5per Mtok out$0.056per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | openai-responses flex | $0.56per Mtok in$4.5per Mtok out$0.056per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregator | openai | $0.62per Mtok in$5per Mtok out$0.062per Mtok cachedrouter.requesty.ai · read 2026-09-14 |
| Requesty aggregatornot on the seller's list today | azure eastus2 | $1.12per Mtok in$9per Mtok out$0.11per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | azure francecentral | $1.24per Mtok in$9.9per Mtok out$0.12per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | azure swedencentral | $1.24per Mtok in$9.9per Mtok out$0.12per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregator | azure | $1.25per Mtok in$10per Mtok out$0.12per Mtok cachedrouter.requesty.ai · read 2026-09-16 |
| Requesty aggregator | openai-responses | $1.25per Mtok in$10per Mtok out$0.12per Mtok cachedrouter.requesty.ai · read 2026-09-11 |
| Nous Research 2 ways | $1.25per Mtok in$10per Mtok out$0.13per Mtok cached | |
| Nous Research aggregator | batch | $0.62per Mtok in$5per Mtok out$0.062per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| Nous Research aggregator | standard | $1.25per Mtok in$10per Mtok out$0.13per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 6 ways | $1.25per Mtok in$10per Mtok out$0.12per Mtok cached | |
| OpenRouter aggregator | batch | $0.62per Mtok in$5per Mtok out$0.062per Mtok cachedopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregatornot on the seller's list today | openai/default/flex | $0.62per Mtok in$5per Mtok out$0.062per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | openai/flex | $0.62per Mtok in$5per Mtok out$0.062per Mtok cachedopenrouter.ai · read 2026-08-26 |
| OpenRouter aggregator | standard | $1.25per Mtok in$10per Mtok out$0.12per Mtok cachedopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | azure | $1.25per Mtok in$10per Mtok out$0.13per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | azure/swedencentral | $1.38per Mtok in$11per Mtok out$0.14per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregatornot on the seller's list today | openai/default/priority | $2.5per Mtok in$20per Mtok out$0.25per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | openai/fast | $2.5per Mtok in$20per Mtok out$0.25per Mtok cachedopenrouter.ai · read 2026-08-26 |
| ElectronHub aggregator | standard | $1per Mtok in$8per Mtok outapi.electronhub.ai · read 2026-09-16 |
Measured 48 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 2ndof 23 | Cl bench — Epoch AI | Overall (high) | 0.237 |
| 2ndof 54 | Live bench — Epoch AI | Global average (high) | 78.79 |
| 4thof 17 | Cl bench life — Epoch AI | Overall (high) | 0.173 |
| 7thof 38 | Vpct — Epoch AI | Correct (high) | 0.587 |
| 10thof 61 | AIME 2025 | Accuracy (± 95% CI) (high) | 94.17 |
| 13thof 46 | Enigma eval — Epoch AI | Accuracy | 11.23 |
| 14thof 51 | Humanity's Last Exam (Epoch AI replication) | Accuracy | 23.68 |
| 14thof 34 | LMArena · Search | Score (Elo) | 1199 |
| 18thof 38 | Gso — Epoch AI | Score OPT@1 | 0.137 |
| 20thof 47 | SWE-bench Verified (default "Bash Only" view, agent = mini-SWE-agent) | % Resolved (medium) | 66 |
| 24thof 101 | FrontierMath (Tiers 1-3) | mean_score (high) | 31.034 |
| 24thof 72 | Frontiermath tier 4 — Epoch AI | mean_score (high) | 12.5 |
| 25thof 262 | MMLU-Pro | Overall (accuracy) | 0.864 |
| 27thof 80 | Simpleqa verified — Epoch AI | mean_score (high) | 48 |
| 27thof 35 | Swe bench verified — Epoch AI | mean_score (high) | 67.975 |
| 29thof 112 | Ale bench — Epoch AI | Performance (high) | 1192.15 |
| 29thof 123 | Lmca — Epoch AI | Score (high) | 43.89 |
| 31stof 161 | Dtbench — Epoch AI | Accuracy (high) | 90.13 |
| 34thof 41 | Deepresearchbench — Epoch AI | Average score (low) | 0.428 |
| 41stof 65 | Apex agents — Epoch AI | Pass@1 score (high) | 0.175 |
| 43rdof 222 | Chess puzzles — Epoch AI | mean_score (high) | 32 |
| 43rdof 60 | Vending bench 2 — Epoch AI | Score | 1473.432 |
| 45thof 152 | LMArena · Vision | Score (Elo) (high) | 1250 |
| 45thof 102 | Simplebench — Epoch AI | Score (AVG@5) (high) | 0.532 |
| 46thof 170 | Weirdml — Epoch AI | Accuracy (high) | 60.77 |
| 55thof 127 | Mystery game puzzles — Epoch AI | mean_score (low) | 19 |
| 57thof 81 | Forecastbench — Epoch AI | Overall score | 58.1 |
| 61stof 109 | Design Arena · svg (models) | Elo | 1174 |
| 63rdof 313 | GPQA Diamond | mean_score (high) | 87.626 |
| 64thof 402 | LMArena · Text | Score (Elo) (high) | 1455 |
| 66thof 152 | Design Arena · dataviz (models) | Elo | 1220 |
| 70thof 155 | Design Arena · gamedev (models) | Elo | 1201 |
| 70thof 290 | OTIS Mock AIME 2024-2025 | mean_score (high) | 88.611 |
| 70thof 105 | Vectara Hallucination Leaderboard | Hallucination Rate | 10.9 |
| 73rdof 92 | Design Arena · asciiart (models) | Elo | 1136 |
| 75thof 202 | Terminalbench — Epoch AI | Accuracy mean | 0.476 |
| 77thof 121 | Webdev arena — Epoch AI | Arena Score (medium) | 1391.01 |
| 80thof 128 | LMArena · WebDev | Score (Elo) (medium) | 1392 |
| 82ndof 177 | Critpt — Epoch AI | Accuracy | 4.857 |
| 83rdof 156 | Design Arena · codecategories (models) | Elo | 1186 |
| 83rdof 162 | Design Arena · website (models) | Elo | 1199 |
| 84thof 150 | Design Arena · uicomponent (models) | Elo | 1181 |
| 90thof 184 | Artificial Analysis · Coding Index | Index | 49.4 |
| 99thof 168 | Scicode — Epoch AI | Score | 43.287 |
| 111thof 227 | Arc agi 2 — Epoch AI | Score (high) | 17.64 |
| 112thof 244 | Arc agi — Epoch AI | Score (high) | 72.83 |
| 114thof 147 | Design Arena · 3d (models) | Elo | 1089 |
| 231stof 656 | Epoch capabilities index — Epoch AI | ECI Score (high) | 149.62 |
About
GPT-5.1 — a text model from OpenAI, sold by 7 companies from $1 in and $8 out per million tokens, placed 2nd of 54 on Live bench — Epoch AI.
It takes text, images and files and returns text, with a context window of 400,000 tokens. It was published in 2025, trained on material up to September 2024. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning, code and agents. Seven companies sell it. The cheapest is $1 in and $8 out per million tokens at ElectronHub. Beside the standard rate there are batch, faster, separately routed, regional and flex lanes. It has been measured on 48 boards, and stands best at 2nd of 54 on Live bench — Epoch AI.
Every current figure
- Maker
- OpenAI
- Register
- model
- Takes
- text + image + file
- Returns
- text
- Context
- 400,000 tokens
- Published
- 2025
- Knowledge to
- September 2024
- Licence
- not read
- Sellers
- 7
- Price
- $1 in and $8 out per million tokens — ElectronHub
- Boards
- 48
- Best place
- 2nd of 54 — Live bench — Epoch AI
Known as 15 names
GPT-5.1 (high)gpt-5.1-searchGPT 5.1 medium5.1GPT 5.1openai/gpt-5.1openai/gpt-5.1:batchazure/gpt-5.1azure/gpt-5.1@eastus2azure/gpt-5.1@francecentralazure/gpt-5.1@swedencentralopenai-responses/gpt-5.1openai-responses/gpt-5.1:flexopenai/gpt-5.1:flexOpenAI: GPT-5.1 (batch)