Skip to main content
Van Data Team
Legacy modelOpenAI

GPT-4o benchmarks, pricing and specs

GPT-4o is an OpenAI model released on May 13, 2024 that takes text, image and audio input and produces text. It is now listed as a legacy model. It costs $2.50 per 1M input tokens and $10 per 1M output tokens and accepts up to 128,000 tokens of context. It scores 1346 Elo on Arena Text (Arena, measured October 8, 2026).

Per 1M input tokens
$2.50
Per 1M output tokens
$10
Context window
128K
Arena Text
1346 Elo

Data verified October 12, 2026 · Dataset 2026-10-12

Share this

Key facts

Provider
OpenAI
Model family
GPT-4o
Release date
May 13, 2024
Status
Legacy
Access
API only
API model id
Not reported
Context window
128,000 tokens
Max output
16,384 tokens
Input
text, image, audio
Output
text
Task families
text, multimodal
Declared capabilities
reasoning

GPT-4o pricing

It is the #11 most expensive of 38 current text models priced per 1M input tokens.

UnitPrice (USD)TierAppliesSource
1M input tokens$2.50standardCurrent
1M output tokens$10standardCurrent
1M input tokens$1.25cachedCurrent

Independent benchmark results

Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. OpenAI's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.

BenchmarkScoreRankMeasuredSource
Arena Text1346 EloNot rankedOctober 8, 2026Arena · 2026-10-12
GPQA Diamond48.9%Not rankedOctober 12, 2026Epoch AI · 2026-10-12

Strengths, cautions and best uses

Strengths

  • GPT-4o records API access for text, image, and audio inputs and a published 128,000-token context window

Cautions

  • This record is marked legacy; confirm current availability and migration requirements before adoption

Best for

  • API trials combining text, images, and audio

Alternatives to GPT-4o

The closest current textmodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.

GPT-4o FAQ

How much does GPT-4o cost?

GPT-4o costs $2.50 per 1M input tokens and $10 per 1M output tokens at the standard tier. It is the #11 most expensive of 38 current text models priced per 1M input tokens. Source: OpenAI, verified August 6, 2026.

What is the context window of GPT-4o?

GPT-4o accepts up to 128,000 tokens of context. It can return up to 16,384 tokens in one response. That ranks #40 of 45 current text models by context length.

How does GPT-4o score on independent benchmarks?

GPT-4o scores 1346 Elo on Arena Text (Arena, measured October 8, 2026) and 48.9% on GPQA Diamond (Epoch AI, measured October 12, 2026). These are independent evaluations, not OpenAI's own launch figures.

Is GPT-4o open source or API only?

GPT-4o is available through OpenAI's API only; its weights are not published.

What are the best alternatives to GPT-4o?

The closest current alternatives by price and measured performance are GPT-6 Luna (96% cheaper per 1M input tokens, $0.10 vs $2.50), GPT-5.4 (same price per 1M input tokens, $2.50), Kimi K3 (20% more per 1M input tokens, $3 vs $2.50) and Claude Sonnet 5 (20% cheaper per 1M input tokens, $2 vs $2.50).

Sources

Cite this page

Van Data Team. "GPT-4o Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-12. https://vandatateam.com/ai-model-benchmarks/gpt-4o

Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.

Production evaluation

Deciding whether GPT-4o fits your workload?

Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.

  • Evaluation cases and acceptance thresholds tied to real work
  • Model routing, fallbacks and cost controls
Compare all modelsDiscuss your evaluation