GPT-5 mini
GPT-5 mini is a cost optimized model that excels at reasoning/chat tasks.
text + image + file → text · made by OpenAI
$0.25→$2per Mtok in / out
OpenAI · 14 sellers
Sold by 30 ways
| Seller | Lane | Rate |
|---|---|---|
| Microsoft Azure AI cloud | batch | $0.14per Mtok in$1.1per Mtok out$0.013per Mtok cachedraw.githubusercontent.com · read 2026-10-31 |
| Databricks cloud | standard | $0.25per Mtok in$2per Mtok out$0.025per Mtok cached$0.25per Mtok cache writemodels.dev · read 2026-10-31 |
| DigitalOcean cloud | standard | $0.25per Mtok in$2per Mtok out$0.025per Mtok cachedmodels.dev · read 2026-10-31 |
| Microsoft Azure AI cloud | standard | $0.25per Mtok in$2per Mtok out$0.025per Mtok cachedmodels.dev · read 2026-10-31 |
| OpenAI api | standard | $0.25per Mtok in$2per Mtok out$0.025per Mtok cacheddevelopers.openai.com · read 2026-08-24 |
| Oracle Cloud Infrastructure cloud | standard | $0.25per Mtok in$2per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| Snowflake Cortex cloud | standard | $0.3per Mtok in$1.2per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| Databricks cloud | priority | $0.45per Mtok in$3.6per Mtok out$0.045per Mtok cachedraw.githubusercontent.com · read 2026-10-31 |
| Microsoft Azure AI cloud | priority | $0.49per Mtok in$3.96per Mtok out$0.05per Mtok cachedraw.githubusercontent.com · read 2026-10-31 |
| Requesty 2 ways | $0.11per Mtok in$0.9per Mtok out$0.011per Mtok cached | |
| Requesty aggregatornot on the seller's list today | openai flex | $0.11per Mtok in$0.9per Mtok out$0.011per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregator | openai | $0.12per Mtok in$1per Mtok out$0.013per Mtok cachedrouter.requesty.ai · read 2026-10-09 |
| Requesty aggregatornot on the seller's list today | azure eastus2 | $0.23per Mtok in$1.8per Mtok out$0.022per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | azure francecentral | $0.25per Mtok in$1.98per Mtok out$0.025per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | azure swedencentral | $0.25per Mtok in$1.98per Mtok out$0.025per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | azure uksouth | $0.25per Mtok in$1.98per Mtok out$0.025per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregator | azure | $0.25per Mtok in$2per Mtok out$0.025per Mtok cachedrouter.requesty.ai · read 2026-10-09 |
| Requesty aggregatornot on the seller's list today | openai-responses | $0.25per Mtok in$2per Mtok out$0.025per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Requesty aggregatornot on the seller's list today | openai priority | $0.41per Mtok in$3.24per Mtok out$0.041per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Nous Research 2 ways | $0.25per Mtok in$2per Mtok out$0.025per Mtok cached | |
| Nous Research aggregator | batch | $0.12per Mtok in$1per Mtok out$0.013per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| Nous Research aggregator | standard | $0.25per Mtok in$2per Mtok out$0.025per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 5 ways | $0.25per Mtok in$2per Mtok out$0.025per Mtok cached | |
| OpenRouter aggregator | batch | $0.12per Mtok in$1per Mtok out$0.013per Mtok cachedopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | openai/flex | $0.12per Mtok in$1per Mtok out$0.013per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | standard | $0.25per Mtok in$2per Mtok out$0.025per Mtok cachedopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | azure | $0.25per Mtok in$2per Mtok out$0.03per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | azure/swedencentral | $0.28per Mtok in$2.2per Mtok out$0.033per Mtok cachedopenrouter.ai · read 2026-08-25 |
| ElectronHub aggregator | standard | $0.25per Mtok in$2per Mtok outapi.electronhub.ai · read 2026-10-31 |
| GitHub Copilot aggregator | standard | $0.25per Mtok in$2per Mtok out$0.025per Mtok cachedmodels.dev · read 2026-10-31 |
| Inference.net aggregator | standard | $0.25per Mtok in$2per Mtok out$0.025per Mtok cachedapi.inference.net · read 2026-10-31 |
| RedPill aggregator | standard | $0.25per Mtok in$2per Mtok outapi.redpill.ai · read 2026-09-20 |
| Vercel AI Gateway aggregator | standard | $0.25per Mtok in$2per Mtok out$0.025per Mtok cachedai-gateway.vercel.sh · read 2026-08-25 |
Measured 46 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 3rdof 108 | Math level 5 — Epoch AI | mean_score (high) | 97.847 |
| 10thof 49 | Lech mazur writing — Epoch AI | Mean score (medium) | 8.31 |
| 15thof 18 | Algotune — Epoch AI | Score (high) | 1.38 |
| 17thof 46 | Enigma eval — Epoch AI | Accuracy | 8.193 |
| 17thof 38 | Vpct — Epoch AI | Correct (medium) | 0.402 |
| 19thof 42 | Fictionlivebench — Epoch AI | 120k token score (medium) | 0.625 |
| 22ndof 56 | Humanity's Last Exam (Epoch AI replication) | Accuracy | 19.44 |
| 28thof 101 | FrontierMath (Tiers 1-3) | mean_score (high) | 27.241 |
| 29thof 35 | Swe bench verified — Epoch AI | mean_score (medium) | 64.669 |
| 31stof 72 | Frontiermath tier 4 — Epoch AI | mean_score (high) | 6.25 |
| 47thof 92 | Forecastbench — Epoch AI | Overall score | 63.3 |
| 57thof 122 | Frontiermath tiers 1 3 v2 — Epoch AI | mean_score (high) | 46.667 |
| 65thof 78 | Frontiermath tier 4 v2 — Epoch AI | mean_score (high) | 12.195 |
| 65thof 173 | Weirdml — Epoch AI | Accuracy (high) | 52.67 |
| 70thof 84 | Proofbench — Epoch AI | Accuracy (high) | 9 |
| 71stof 71 | Vending bench 2 — Epoch AI | Score | -31.184 |
| 76thof 93 | Design Arena · asciiart (models) | Elo | 1122 |
| 77thof 93 | Simpleqa verified — Epoch AI | mean_score (high) | 21.6 |
| 78thof 132 | Ale bench — Epoch AI | Performance (high) | 799.77 |
| 81stof 154 | Chess puzzles — Epoch AI | mean_score (high) | 24 |
| 90thof 111 | Vectara Hallucination Leaderboard | Hallucination Rate | 12.9 |
| 92ndof 114 | Design Arena · svg (models) | Elo | 1088 |
| 95thof 131 | Artificial Analysis · Agentic Index | Index | 6.8 |
| 97thof 306 | OTIS Mock AIME 2024-2025 | mean_score (high) | 86.667 |
| 103rdof 165 | LMArena · Vision | Score (Elo) (high) | 1183 |
| 114thof 162 | Design Arena · gamedev (models) | Elo | 1128 |
| 115thof 142 | Mystery game puzzles — Epoch AI | mean_score (minimal) | 10 |
| 117thof 154 | Design Arena · dataviz (models) | Elo | 1131 |
| 119thof 157 | Design Arena · uicomponent (models) | Elo | 1101 |
| 122ndof 202 | Terminalbench — Epoch AI | Accuracy mean | 0.348 |
| 126thof 150 | Design Arena · 3d (models) | Elo | 1034 |
| 126thof 169 | Design Arena · website (models) | Elo | 1124 |
| 128thof 163 | Design Arena · codecategories (models) | Elo | 1113 |
| 130thof 197 | Lmca — Epoch AI | Score (high) | 34.2 |
| 131stof 235 | Dtbench — Epoch AI | Accuracy (high) | 80.53 |
| 142ndof 163 | Artificial Analysis · Coding Index | Index | 15.6 |
| 165thof 326 | GPQA Diamond | mean_score (high) | 75 |
| 172ndof 282 | ARC-AGI-2 (Public Eval) | Score (%) (high) | 5.83 |
| 175thof 273 | ARC-AGI-1 (Public Eval) | Score (%) (high) | 61.52 |
| 175thof 414 | LMArena · Text | Score (Elo) (high) | 1390 |
| 185thof 235 | Scicode — Epoch AI | Score | 39.236 |
| 187thof 298 | ARC-AGI-1 (Semi-Private) | Score (%) (high) | 54.33 |
| 198thof 309 | Arc agi — Epoch AI | Score (high) | 54.33 |
| 201stof 298 | ARC-AGI-2 (Semi-Private) | Score (%) (high) | 4.44 |
| 203rdof 290 | Arc agi 2 — Epoch AI | Score (high) | 4.44 |
| 231stof 260 | Critpt — Epoch AI | Accuracy | 0 |
About
GPT-5 mini — a text model from OpenAI, sold by 14 companies from $0.25 in and $2 out per million tokens, placed 3rd 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 May 2024. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning and agents. Fourteen companies sell it. The cheapest is $0.25 in and $2 out per million tokens at Databricks. Beside the standard rate there are faster, batch, separately routed, regional and flex lanes. It has been measured on 46 boards, and stands best at 3rd 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
- May 2024
- Licence
- not read
- Sellers
- 14
- Price
- $0.25 in and $2 out per million tokens — Databricks
- Boards
- 46
- Best place
- 3rd of 108 — Math level 5 — Epoch AI
Known as 17 names
GPT-5-mini-2025-08-07 (FC)GPT-5 mini (high)GPT-5-mini5 miniGPT 5 Miniopenai/gpt-5-miniopenai/gpt-5-mini:batchazure/gpt-5-miniazure/gpt-5-mini@eastus2azure/gpt-5-mini@francecentralazure/gpt-5-mini@swedencentralazure/gpt-5-mini@uksouthopenai-responses/gpt-5-miniopenai/gpt-5-mini:flexopenai/gpt-5-mini:priorityopenai/gpt-5-mini-batchOpenAI: GPT-5 Mini (batch)