Enterprise DNAEnterprise DNA
OpenAI logo

Models · Best cheap

GPT-4o-mini

by OpenAI

GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.

Visit OpenAI ↗

Our verdict

Not reviewed yet

We have not reviewed GPT-4o-mini yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About GPT-4o-mini

GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.

Best for

Cost-efficient product features and multimodal volume

Use cases

  • chat UIs
  • vision QA
  • extraction
  • light coding agents

Enterprise DNA angle

Many EDNA product surfaces start on 4o-mini; Omni keeps fallbacks and evals consistent.

Notes

GPT-4o-mini is listed in the EDNA Models directory from the OpenRouter catalogue.

Pros

  • Low cost multimodal workhorse
  • Huge ecosystem and SDK familiarity
  • Solid for product features at scale

Cons

  • Not the top pick for hardest reasoning
  • Closed weights

Key facts

What we have checked

Input price
$0.150 per million tokens
Checked OpenRouter models API
Output price
$0.600 per million tokens
Checked OpenRouter models API
Price on azure
$0.075 per million cached input tokens
Checked OpenRouter models API
Price on azure
$0.150 per million input tokens
Checked OpenRouter models API
Price on azure
$0.600 per million output tokens
Checked OpenRouter models API
Price on openai
$0.075 per million cached input tokens
Checked OpenRouter models API
Price on openai
$0.150 per million input tokens
Checked OpenRouter models API
Price on openai
$0.600 per million output tokens
Checked OpenRouter models API
Latest version
openai/gpt-4o-mini
Checked OpenRouter models API
Gpqa diamond
37.7% (for 18 July 2024)
Checked Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private
0.7% (for 18 July 2024)
Checked Epoch AI (CC BY 4.0)
Simpleqa verified
8.3% (for 18 July 2024)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `openai/gpt-4o-mini`.

  • openrouter · openai/gpt-4o-mini · Docs

OpenRouter id: openai/gpt-4o-mini

Price

What GPT-4o-mini costs, over time

Input price

$0.150 to $0.150

US dollars per million input tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Output price

$0.600 to $0.600

US dollars per million output tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
azureCached input$0.075 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
azureInput$0.150 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
azureOutput$0.600 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
openaiCached input$0.075 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
openaiInput$0.150 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
openaiOutput$0.600 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much GPT-4o-mini is used

Tokens served a day

29B to 31.6B

tokens a day on OpenRouter. 19 Sept 2026 to 10 Nov 2026, 53 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How GPT-4o-mini scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index6.7indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index11.4indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,286EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
LMArena vision rating (Elo)1,066EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
Aider polyglot (best-across-versions)3.6percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Arc agi 2 (best-across-versions)0percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Balrog (best-across-versions)17.4percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Chess puzzles (best-across-versions)3percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)54.4percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private (best-across-versions)0.7percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Geobench (best-across-versions)64percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)37.7percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Show 12 more scores
ScoreValueSourceChecked
Gsm8k (best-across-versions)91.3percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Lech mazur writing (best-across-versions)67.2percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Lmca (best-across-versions)10.4percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Math level 5 (best-across-versions)52.6percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Mmlu (best-across-versions)81.8percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Mystery game puzzles (best-across-versions)12percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated6.9percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Piqa (best-across-versions)88.7percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Simplebench (best-across-versions)10.7percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Simpleqa verified (best-across-versions)8.3percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Vpct (best-across-versions)34percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Weirdml (best-across-versions)11.8percentAs of 18 July 2024Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.

USAGE / OPENROUTER

How much GPT-4o-mini is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
196B ▼10.3%
Requests, last 7 days
83.4M
Tool calls, last 7 days
2.7M
People's vote
1286
Average cost per request
2.9¢
Price per million tokens
$0.15 in · $0.6 out
025B50B19 Sept: 29B tokens, 11.1M requests20 Sept: 25.9B tokens, 10.7M requests21 Sept: 37.2B tokens, 15.2M requests22 Sept: 36.7B tokens, 15.8M requests23 Sept: 38.2B tokens, 14.8M requests24 Sept: 35.9B tokens, 15.4M requests25 Sept: 34B tokens, 13.6M requests26 Sept: 35.5B tokens, 10.6M requests27 Sept: 23.1B tokens, 9.8M requests28 Sept: 31B tokens, 12.7M requests29 Sept: 38.2B tokens, 17.9M requests30 Sept: 47.6B tokens, 16.8M requests1 Oct: 38.6B tokens, 20.8M requests2 Oct: 34B tokens, 16.7M requests3 Oct: 27.8B tokens, 11.7M requests4 Oct: 24.8B tokens, 10.5M requests5 Oct: 30.7B tokens, 14.4M requests6 Oct: 32B tokens, 13.2M requests7 Oct: 29.7B tokens, 13M requests8 Oct: 31.7B tokens, 13.6M requests9 Oct: 31B tokens, 13.8M requests10 Oct: 28.5B tokens, 11.8M requests11 Oct: 28.4B tokens, 11.1M requests12 Oct: 32.2B tokens, 13.1M requests13 Oct: 27.9B tokens, 12.2M requests14 Oct: 31B tokens, 13.8M requests15 Oct: 36.7B tokens, 16.3M requests16 Oct: 34.1B tokens, 16.2M requests17 Oct: 28.1B tokens, 10.6M requests18 Oct: 27.2B tokens, 10.3M requests19 Oct: 31.9B tokens, 12.8M requests20 Oct: 29.7B tokens, 13.1M requests21 Oct: 30.4B tokens, 13.9M requests22 Oct: 27.3B tokens, 12M requests23 Oct: 28.3B tokens, 14.6M requests24 Oct: 25.1B tokens, 13.3M requests25 Oct: 22.6B tokens, 11.5M requests26 Oct: 27.8B tokens, 13.8M requests27 Oct: 29.6B tokens, 13.8M requests28 Oct: 28B tokens, 13.5M requests29 Oct: 28.2B tokens, 13.5M requests30 Oct: 32.3B tokens, 14.8M requests31 Oct: 25.2B tokens, 12M requests1 Nov: 32.5B tokens, 12.8M requests2 Nov: 36.6B tokens, 14.8M requests3 Nov: 35.4B tokens, 14.2M requests4 Nov: 34.1B tokens, 14.8M requests5 Nov: 30.6B tokens, 13.1M requests6 Nov: 31.5B tokens, 12M requests7 Nov: 21B tokens, 9.3M requests8 Nov: 19.6B tokens, 8.2M requests9 Nov: 27.4B tokens, 11.9M requests10 Nov: 31.6B tokens, 14.2M requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with GPT-4o-mini.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-07. Hosting routes and app features can differ.

DeveloperOpenAI
Exact model identifieropenai/gpt-4o-mini
Inputtext, image, file
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Not established
Availability
available
Price basis
token
Licence verification
Check the developer licence; the model name is insufficient
Context length
128K tokens
Knowledge cutoff
31 Oct 2023
Developer release date
Not established
First seen in the catalogue
18 Jul 2024
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

openai/gpt-4o-mini: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-07
openrouter.ai ↗

Source for first seen, tool calling, context length, input, knowledge cutoff, output, structured output.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Build an appWorkflow & starter prompt ↗Extract document dataWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Coding Index: 11.4 (2026-11-09) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →