o4-mini
A customer fine-tuned deployment of OpenAI's o4-mini.
text + image + file → text · made by OpenAI
$1.1→$4.4per Mtok in / out
OpenAI · 7 sellers
Sold by 19 ways
| Seller | Lane | Rate |
|---|---|---|
| Microsoft Azure AI cloud | batch | $0.55per Mtok in$2.2per Mtok outprices.azure.com · read 2026-08-24 |
| Microsoft Azure AI cloud | standard | $1.1per Mtok in$4.4per Mtok out$0.28per Mtok cachedmodels.dev · read 2026-09-16 |
| Microsoft Azure AI 0 ways | $1.1per Mtok in$4.4per Mtok out$0.28per Mtok cached | |
| Microsoft Azure AI cloudnot on the seller's list today | fine-tuned | $1.1per Mtok in$4.4per Mtok out$0.28per Mtok cachedprices.azure.com · read 2026-08-25 |
| OpenAI api | standard | $1.1per Mtok in$4.4per Mtok out$0.28per Mtok cacheddevelopers.openai.com · read 2026-08-24 |
| Requesty 3 ways | $0.49per Mtok in$1.98per Mtok out$0.12per Mtok cached | |
| Requesty aggregatornot on the seller's list today | openai flex | $0.49per Mtok in$1.98per Mtok out$0.12per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | azure westus3 | $0.99per Mtok in$3.96per Mtok out$0.25per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | openai low | $0.99per Mtok in$3.96per Mtok out$0.25per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | openai medium | $0.99per Mtok in$3.96per Mtok out$0.25per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | azure francecentral | $1.09per Mtok in$4.36per Mtok out$0.27per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | azure swedencentral | $1.09per Mtok in$4.36per Mtok out$0.27per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregator | azure | $1.1per Mtok in$4.4per Mtok out$0.28per Mtok cachedrouter.requesty.ai · read 2026-09-16 |
| Requesty aggregator | openai | $1.1per Mtok in$4.4per Mtok out$0.28per Mtok cachedrouter.requesty.ai · read 2026-09-14 |
| Requesty aggregator | openai-responses | $1.1per Mtok in$4.4per Mtok out$0.28per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Nous Research 2 ways | $1.1per Mtok in$4.4per Mtok out$0.28per Mtok cached | |
| Nous Research aggregator | batch | $0.55per Mtok in$2.2per Mtok out$0.14per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| Nous Research aggregator | standard | $1.1per Mtok in$4.4per Mtok out$0.28per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 2 ways | $1.1per Mtok in$4.4per Mtok out$0.28per Mtok cached | |
| OpenRouter aggregator | batch | $0.55per Mtok in$2.2per Mtok out$0.14per Mtok cachedopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | standard | $1.1per Mtok in$4.4per Mtok out$0.28per Mtok cachedopenrouter.ai · read 2026-08-24 |
| ElectronHub aggregator | standard | $0.8per Mtok in$3.2per Mtok outapi.electronhub.ai · read 2026-09-16 |
| Vercel AI Gateway aggregator | standard | $1.1per Mtok in$4.4per Mtok out$0.28per Mtok cachedai-gateway.vercel.sh · read 2026-08-25 |
Measured 48 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 3rdof 15 | Cad eval — Epoch AI | Overall pass (%) (medium) | 0.62 |
| 3rdof 28 | LiveCodeBench Leaderboard (default window 8/1/2024–5/1/2025, 454 problems) | Pass@1 | 74.2 |
| 4thof 108 | Math level 5 — Epoch AI | mean_score (high) | 97.829 |
| 5thof 81 | Forecastbench — Epoch AI | Overall score | 61.8 |
| 5thof 22 | SWE-bench Multimodal | % Resolved | 33.85 |
| 6thof 18 | Algotune — Epoch AI | Score (high) | 1.72 |
| 8thof 11 | Gdpval — Epoch AI | Win Rate (%) (high) | 0.253 |
| 8thof 38 | Vpct — Epoch AI | Correct (medium) | 0.575 |
| 16thof 46 | Enigma eval — Epoch AI | Accuracy (high) | 9.21 |
| 18thof 72 | Aider polyglot — Epoch AI | Percent correct (high) | 72 |
| 19thof 25 | AgentBench Leaderboard (new) | Success Rate (pass@1) AVG | 39.7 |
| 19thof 50 | Metr time horizons — Epoch AI | average_score (medium) | 0.639 |
| 20thof 42 | Fictionlivebench — Epoch AI | 120k token score (medium) | 0.625 |
| 21stof 109 | Berkeley Function-Calling Leaderboard (BFCL) V4 | Overall Acc (fc) | 53.24 |
| 21stof 51 | Humanity's Last Exam (Epoch AI replication) | Accuracy (high) | 18.08 |
| 33rdof 72 | Frontiermath tier 4 — Epoch AI | mean_score (high) | 6.25 |
| 33rdof 49 | Lech mazur writing — Epoch AI | Mean score (medium) | 7.5 |
| 34thof 101 | FrontierMath (Tiers 1-3) | mean_score (high) | 24.828 |
| 34thof 38 | Gso — Epoch AI | Score OPT@1 (high) | 0.036 |
| 53rdof 62 | Frontiermath tier 4 v2 — Epoch AI | mean_score (high) | 4.878 |
| 53rdof 106 | Frontiermath tiers 1 3 v2 — Epoch AI | mean_score (high) | 36.14 |
| 55thof 112 | Ale bench — Epoch AI | Performance (high) | 826.17 |
| 60thof 222 | Chess puzzles — Epoch AI | mean_score (high) | 26 |
| 63rdof 170 | Weirdml — Epoch AI | Accuracy (high) | 52.56 |
| 67thof 80 | Simpleqa verified — Epoch AI | mean_score (low) | 19.6 |
| 73rdof 161 | Dtbench — Epoch AI | Accuracy (high) | 77.6 |
| 74thof 102 | Simplebench — Epoch AI | Score (AVG@5) (high) | 0.387 |
| 75thof 123 | Lmca — Epoch AI | Score (high) | 26.5 |
| 79thof 152 | LMArena · Vision | Score (Elo) | 1200 |
| 95thof 105 | Vectara Hallucination Leaderboard | Hallucination Rate | 18.6 |
| 102ndof 290 | OTIS Mock AIME 2024-2025 | mean_score (high) | 81.667 |
| 103rdof 205 | ARC-AGI-1 (Public Eval) | Score (%) (high) | 68.03 |
| 110thof 216 | ARC-AGI-2 (Public Eval) | Score (%) (high) | 7.52 |
| 118thof 127 | Mystery game puzzles — Epoch AI | mean_score (high) | 5 |
| 120thof 230 | ARC-AGI-1 (Semi-Private) | Score (%) (high) | 58.67 |
| 120thof 177 | Critpt — Epoch AI | Accuracy (high) | 0.6 |
| 124thof 313 | GPQA Diamond | mean_score (high) | 79.609 |
| 131stof 232 | ARC-AGI-2 (Semi-Private) | Score (%) (high) | 6.11 |
| 131stof 244 | Arc agi — Epoch AI | Score (high) | 58.67 |
| 133rdof 227 | Arc agi 2 — Epoch AI | Score (high) | 6.11 |
| 133rdof 150 | Design Arena · uicomponent (models) | Elo | 998 |
| 134thof 155 | Design Arena · gamedev (models) | Elo | 1026 |
| 138thof 152 | Design Arena · dataviz (models) | Elo | 1006 |
| 142ndof 147 | Design Arena · 3d (models) | Elo | 882 |
| 145thof 156 | Design Arena · codecategories (models) | Elo | 991 |
| 147thof 162 | Design Arena · website (models) | Elo | 998 |
| 160thof 402 | LMArena · Text | Score (Elo) | 1391 |
| 312thof 656 | Epoch capabilities index — Epoch AI | ECI Score (low) | 145.67 |
About
o4-mini — a text model from OpenAI, sold by 7 companies from $0.8 in and $3.2 out per million tokens, placed 4th of 108 on Math level 5 — Epoch AI.
It takes text, images and files and returns text, with a context window of 200,000 tokens. It was published in June 2024, 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, code and agents. Seven companies sell it. The cheapest is $0.8 in and $3.2 out per million tokens at ElectronHub. Beside the standard rate there are batch and separately routed lanes. It has been measured on 48 boards, and stands best at 4th of 108 on Math level 5 — Epoch AI.
Every current figure
- Maker
- OpenAI
- Register
- model
- Takes
- text + image + file
- Returns
- text
- Context
- 200,000 tokens
- Longest answer
- 100,000 tokens
- Published
- June 2024
- Knowledge to
- May 2024
- Licence
- not read
- Sellers
- 7
- Price
- $0.8 in and $3.2 out per million tokens — ElectronHub
- Boards
- 48
- Best place
- 4th of 108 — Math level 5 — Epoch AI
Known as 18 names
o4-mini (2025-04-16)o4-mini-2025-04-16 (FC)o4-mini (medium)O4-Mini (Low)GUIRepair + o4-mini (2025-04-16)o4-mini 0416o4-mini-ftopenai/o4-miniopenai/o4-mini:batchazure/o4-mini@eastus2azure/o4-mini@francecentralazure/o4-mini@swedencentralazure/o4-mini@westus3openai-responses/o4-miniopenai/o4-mini:flexopenai/o4-mini:lowopenai/o4-mini:mediumOpenAI: o4 Mini (batch)