GPT-5
GPT-5 is OpenAI's flagship language model that excels at complex reasoning, broad real-world knowledge, code-intensive, and multi-step agentic tasks.
text + image + file → text · made by OpenAI
$1.25→$10per Mtok in / out
OpenAI · 11 sellers
Sold by 27 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock 0 ways | $0.3per Mtok in$1.2per Mtok out | |
| AWS Bedrock cloudnot on the seller's list today | standard | $0.3per Mtok in$1.2per Mtok outraw.githubusercontent.com · read 2026-08-29 |
| Microsoft Azure AI cloud | batch | $0.62per Mtok in$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 |
| DigitalOcean cloud | standard | $1.25per Mtok in$10per Mtok out$0.12per Mtok cachedmodels.dev · read 2026-09-16 |
| Microsoft Azure AI cloud | standard | $1.25per Mtok in$10per Mtok out$0.13per 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 |
| Oracle Cloud Infrastructure cloud | standard | $1.25per Mtok in$10per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Snowflake Cortex cloud | standard | $1.25per Mtok in$10per Mtok out$0.12per Mtok cachedraw.githubusercontent.com · read 2026-09-16 |
| Microsoft Azure AI cloud | priority | $2.5per Mtok in$20per Mtok out$0.25per Mtok cachedprices.azure.com · read 2026-08-24 |
| Avian 0 ways | $0.27per Mtok in$1.08per Mtok out$0.15per Mtok cached | |
| Avian aggregatornot on the seller's list today | standard | $0.27per Mtok in$1.08per Mtok out$0.15per Mtok cachedapi.avian.io · read 2026-08-30 |
| 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 | 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 aggregatornot on the seller's list today | azure uksouth | $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 2026-09-15 |
| Requesty aggregator | openai | $1.25per Mtok in$10per Mtok out$0.12per Mtok cachedrouter.requesty.ai · read 2026-09-14 |
| Requesty aggregator | openai-responses | $1.25per Mtok in$10per Mtok out$0.12per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Requesty aggregatornot on the seller's list today | openai priority | $2.25per Mtok in$18per Mtok out$0.23per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Nous Research 2 ways | $1.25per Mtok in$10per Mtok out$0.12per 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$0.12per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 3 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 aggregator | standard | $1.25per Mtok in$10per Mtok out$0.12per Mtok cachedopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | azure/swedencentral | $1.38per Mtok in$11per Mtok out$0.14per Mtok cachedopenrouter.ai · read 2026-08-25 |
| ElectronHub aggregator | standard | $1per Mtok in$8per Mtok outapi.electronhub.ai · read 2026-09-16 |
| Vercel AI Gateway aggregator | standard | $1.25per Mtok in$10per Mtok out$0.12per Mtok cachedai-gateway.vercel.sh · read 2026-08-25 |
| PPIO 0 ways | $2.1per Mtok in$8.4per Mtok out | |
| PPIO aggregatornot on the seller's list today | standard | $2.1per Mtok in$8.4per Mtok outapi.ppinfra.com · read 2026-08-30 |
Measured 68 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 1stof 69 | Aider polyglot coding leaderboard | Percent correct (high) | 88 |
| 1stof 72 | Aider polyglot — Epoch AI | Percent correct (high) | 88 |
| 1stof 49 | Lech mazur writing — Epoch AI | Mean score (medium) | 8.6 |
| 1stof 108 | Math level 5 — Epoch AI | mean_score (high) | 98.131 |
| 2ndof 42 | Fictionlivebench — Epoch AI | 120k token score (medium) | 0.969 |
| 2ndof 10 | Humanity's Last Exam | Accuracy (%) | 25.3 |
| 5thof 38 | Vpct — Epoch AI | Correct (high) | 0.66 |
| 6thof 11 | Gdpval — Epoch AI | Win Rate (%) (medium) | 0.348 |
| 8thof 61 | AIME 2025 | Accuracy (± 95% CI) (high) | 95 |
| 8thof 18 | Algotune — Epoch AI | Score (high) | 1.67 |
| 10thof 81 | Forecastbench — Epoch AI | Overall score | 61.4 |
| 10thof 25 | SWE-Bench Pro (Public Dataset) | Resolve Rate (high) | 41.78 |
| 11thof 25 | AgentBench Leaderboard (new) | Success Rate (pass@1) AVG | 52.2 |
| 11thof 51 | Humanity's Last Exam (Epoch AI replication) | Accuracy (high) | 25.32 |
| 11thof 13 | Rli — Epoch AI | Score | 1.67 |
| 12thof 36 | Balrog — Epoch AI | Average progress (minimal) | 0.328 |
| 12thof 41 | Deepresearchbench — Epoch AI | Average score (low) | 0.496 |
| 12thof 50 | Metr time horizons — Epoch AI | average_score (medium) | 0.696 |
| 14thof 46 | Enigma eval — Epoch AI | Accuracy | 10.47 |
| 15thof 21 | Ebr bench — Epoch AI | mean_score (high) | 12.698 |
| 16thof 54 | Live bench — Epoch AI | Global average (max) | 62.29 |
| 16thof 262 | MMLU-Pro | Overall (accuracy) (high) | 0.871 |
| 19thof 180 | SWE-bench Verified (Bash Only toggle off — all agents) | % Resolved | 74.4 |
| 20thof 110 | OSWorld-Verified Results (All) | Success Rate (Avg±Std) | 65.8 |
| 20thof 35 | Swe bench verified — Epoch AI | mean_score (high) | 73.554 |
| 21stof 47 | SWE-bench Verified (default "Bash Only" view, agent = mini-SWE-agent) | % Resolved (medium) | 65 |
| 21stof 80 | Simpleqa verified — Epoch AI | mean_score (high) | 50.1 |
| 22ndof 101 | FrontierMath (Tiers 1-3) | mean_score (high) | 32.414 |
| 23rdof 38 | Gso — Epoch AI | Score OPT@1 (high) | 0.069 |
| 25thof 72 | Frontiermath tier 4 — Epoch AI | mean_score (high) | 12.5 |
| 29thof 161 | Dtbench — Epoch AI | Accuracy (high) | 90.67 |
| 30thof 34 | LMArena · Search | Score (Elo) | 1133 |
| 33rdof 112 | Ale bench — Epoch AI | Performance (high) | 1162.45 |
| 35thof 222 | Chess puzzles — Epoch AI | mean_score (high) | 37 |
| 35thof 123 | Lmca — Epoch AI | Score (high) | 39.99 |
| 36thof 106 | Frontiermath tiers 1 3 v2 — Epoch AI | mean_score (high) | 55.439 |
| 39thof 65 | Apex agents — Epoch AI | Pass@1 score (high) | 0.183 |
| 39thof 64 | Proofbench — Epoch AI | Accuracy (high) | 18 |
| 39thof 102 | Simplebench — Epoch AI | Score (AVG@5) (high) | 0.567 |
| 40thof 109 | Design Arena · svg (models) | Elo | 1213 |
| 41stof 62 | Frontiermath tier 4 v2 — Epoch AI | mean_score (high) | 21.951 |
| 43rdof 127 | Mystery game puzzles — Epoch AI | mean_score (high) | 23 |
| 47thof 170 | Weirdml — Epoch AI | Accuracy (high) | 60.7 |
| 49thof 402 | LMArena · Text | Score (Elo) (max) | 1465 |
| 57thof 290 | OTIS Mock AIME 2024-2025 | mean_score (high) | 91.389 |
| 58thof 177 | Critpt — Epoch AI | Accuracy (high) | 12.6 |
| 58thof 152 | Design Arena · dataviz (models) | Elo | 1237 |
| 63rdof 92 | Design Arena · asciiart (models) | Elo | 1158 |
| 68thof 155 | Design Arena · gamedev (models) | Elo | 1208 |
| 68thof 121 | Webdev arena — Epoch AI | Arena Score (medium) | 1419.14 |
| 69thof 128 | LMArena · WebDev | Score (Elo) (medium) | 1420 |
| 72ndof 152 | LMArena · Vision | Score (Elo) (high) | 1211 |
| 73rdof 202 | Terminalbench — Epoch AI | Accuracy mean | 0.496 |
| 74thof 313 | GPQA Diamond | mean_score (high) | 86.174 |
| 77thof 150 | Design Arena · uicomponent (models) | Elo | 1195 |
| 86thof 162 | Design Arena · website (models) | Elo | 1197 |
| 90thof 156 | Design Arena · codecategories (models) | Elo | 1183 |
| 91stof 105 | Vectara Hallucination Leaderboard | Hallucination Rate | 14.7 |
| 101stof 168 | Scicode — Epoch AI | Score | 42.94 |
| 103rdof 216 | ARC-AGI-2 (Public Eval) | Score (%) (high) | 9.58 |
| 109thof 205 | ARC-AGI-1 (Public Eval) | Score (%) (high) | 65.88 |
| 111thof 230 | ARC-AGI-1 (Semi-Private) | Score (%) (high) | 65.67 |
| 116thof 147 | Design Arena · 3d (models) | Elo | 1084 |
| 117thof 232 | ARC-AGI-2 (Semi-Private) | Score (%) (high) | 9.86 |
| 117thof 184 | Artificial Analysis · Coding Index | Index | 37.8 |
| 121stof 227 | Arc agi 2 — Epoch AI | Score (high) | 9.86 |
| 121stof 244 | Arc agi — Epoch AI | Score (high) | 65.67 |
| 223rdof 656 | Epoch capabilities index — Epoch AI | ECI Score (low) | 150 |
About
GPT-5 — a text model from OpenAI, sold by 11 companies from $1 in and $8 out per million tokens, placed 1st of 108 on Math level 5 — 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. Eleven companies sell it. The cheapest is $1 in and $8 out per million tokens at ElectronHub. Beside the standard rate there are batch, faster, regional and separately routed lanes. It has been measured on 68 boards, and stands best at 1st of 108 on Math level 5 — 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
- 11
- Price
- $1 in and $8 out per million tokens — ElectronHub
- Boards
- 68
- Best place
- 1st of 108 — Math level 5 — Epoch AI
Known as 23 names
GPT-5 (2025-08-07)gpt-5 (high)gpt-5 (low)gpt-5 (medium)gpt-5-searchGPT-5(high)GTA1 w/ GPT-5OS-Symphony w/ GPT-5gpt-5-2025-08-07 (High)GPT 5 medium5GPT 5openai/gpt-5openai/gpt-5:batchazure/gpt-5azure/gpt-5@eastus2azure/gpt-5@francecentralazure/gpt-5@swedencentralazure/gpt-5@uksouthopenai-responses/gpt-5openai/gpt-5:flexopenai/gpt-5:priorityOpenAI: GPT-5 (batch)