The Token Tape

ModelsOpenAI

GPT-4o

openrouterprice docs

Context

128K

tokens

Released

May 13, 2024

on OpenRouter

Pricing

Price per million tokens

Input $/MTok

$5.00100%

OpenRouter · Jul 20, 2026

Output $/MTok

$15.0050%

OpenRouter · Jul 20, 2026

Current GPT-4o prices per million tokens across tracked sources.
SourceTracked slugIn $/MTokOut $/MTokCache readCache writeContextEffectiveLast Δ (in)
OpenRouteropenai/gpt-4o-2024-05-13$5.00$15.00——128KJul 20, 2026100%
models.devabacus/gpt-4o-mini$0.15$0.6——128KJul 20, 202694%
llm-prices.comgpt-4o-mini$0.15$0.6$0.075——Jul 19, 202694%

latest tracked price per source · Δ = most recent input-price move within that source

3 sources tracking

Input $/MTok

Output $/MTok

per-source step lines · $/MTok

history since Jan 1, 2023

Specs

Context & availability

GPT-4o specifications.
ProviderOpenAI
Context window128K tokens
Listed on OpenRouterMay 13, 2024
Tracked price sourcesllm-prices.com · OpenRouter · models.dev
OpenRouter slugsopenai/gpt-4o

source: OpenRouter model catalog + tracked price feeds

id: gpt-4o

Usage

Share of OpenRouter tokens

90-day daily

usage share pending — this model isn't in the tracked OpenRouter model rankings yet

Benchmarks

Benchmark results

Benchmark scores for GPT-4o.
BenchmarkConfigurationScoreDateSource
swe-bench-multimodalGUIRepair gpt4o30.8%May 31, 2025swebench-experiments
Aider Polyglotgpt-4o-2024-08-0623.1%Dec 30, 2024aider-repo
Aider Polyglotgpt-4o-2024-11-2018.2%Dec 30, 2024aider-repo
Aider Polyglotgpt-4o-mini-2024-07-183.6%Dec 21, 2024aider-repo
aider-o1-polyglotgpt-4o-2024-11-2015.1%Dec 21, 2024aider-repo
aider-o1-polyglotgpt-4o-mini-2024-07-183.6%Dec 21, 2024aider-repo
aider-editgpt-4o-2024-11-2071.4%Nov 20, 2024aider-repo
SWE-bench Litecodeshelltester gpt4o31.3%Nov 11, 2024swebench-experiments
SWE-bench Liteagentless 1.5 gpt4o32%Oct 28, 2024swebench-experiments
SWE-bench Verifiedepam ai run gpt 4o27%Oct 16, 2024swebench-experiments
swe-bench-multimodalSWE agent M gpt4o12.3%Oct 6, 2024swebench-experiments
swe-bench-multimodalRAG gpt4o6.1%Oct 6, 2024swebench-experiments
swe-bench-multimodalAgentless gpt4o3.1%Oct 6, 2024swebench-experiments
swe-bench-multimodalSWE agent JS gpt4o9.4%Oct 6, 2024swebench-experiments
swe-bench-multimodalSWE agent gpt4o12.2%Oct 6, 2024swebench-experiments
SWE-bench Verifiedepam ai run gpt 4o24%Aug 20, 2024swebench-experiments
SWE-bench LiteRepoGraph gpt4o29.7%Aug 8, 2024swebench-experiments
aider-editgpt-4o-2024-08-0671.4%Aug 6, 2024aider-repo
aider-refactorgpt-4o-2024-08-0649.4%Aug 6, 2024aider-repo
swe-bench-testsweagent gpt4o12%Jul 28, 2024swebench-experiments
SWE-bench Litesweagent gpt4o18.3%Jul 28, 2024swebench-experiments
SWE-bench Litemarscode agent dev34%Jul 23, 2024swebench-experiments
aider-editgpt-4o-mini55.6%Jul 18, 2024aider-repo
SWE-bench Litesima gpt4o27.7%Jul 6, 2024swebench-experiments
SWE-bench Liteagentless gpt4o27.3%Jun 30, 2024swebench-experiments
swe-bench-testautocoderover v2024062018.8%Jun 28, 2024swebench-experiments
SWE-bench Liteabanteai mentatbot gpt4o38%Jun 27, 2024swebench-experiments
SWE-bench Liteautocoderover v2024062030.7%Jun 21, 2024swebench-experiments
SWE-bench Litemoatless gpt4o24.7%Jun 17, 2024swebench-experiments
SWE-bench Liteappmap navie gpt4o21.7%Jun 15, 2024swebench-experiments
swe-bench-testappmap navie gpt4o14.6%Jun 15, 2024swebench-experiments
SWE-bench LiteMASAI gpt4o27.3%Jun 12, 2024swebench-experiments
aider-refactorgpt-4o62.9%May 13, 2024aider-repo
aider-editgpt-4o-2024-05-1372.9%May 13, 2024aider-repo
AA Coding Indexopenai/gpt-4o-2024-05-1324.2index—or-embedded-aa
AA Coding Indexopenai/gpt-4o-mini11.4index—or-embedded-aa
AA Agentic Indexopenai/gpt-4o-mini1index—or-embedded-aa

scores as published by each benchmark; configurations differ — compare within a row's benchmark only

latest result May 31, 2025

Alternatives

Similar models

Alternatives to GPT-4o by OpenRouter usage-rank proximity.
#ModelTokens/day7d ΔHead-to-head
1
DeepSeek V4 FlashDeepSeek
2.7T18.7%vs GPT-4o
2
Hy3Tencent
1.3T11.6%vs GPT-4o
5
Nemotron 3 UltraNVIDIA
733B106.3%vs GPT-4o
7
GLM 5.2Z.ai
533B41%vs GPT-4o

ranked by OpenRouter usage-rank proximity

snapshot Aug 20, 2026

FAQ

GPT-4o FAQ

How much does GPT-4o cost per token?
GPT-4o is priced at $5.00 per million input tokens and $15.00 per million output tokens, per OpenRouter as of Jul 20, 2026.
What is GPT-4o's context window?
GPT-4o supports a context window of up to 128K tokens, per OpenAI.
How good is GPT-4o at coding?
GPT-4o scores 30.8% on swe-bench-multimodal (May 31, 2025). Its full benchmark table is above.
What are the alternatives to GPT-4o?
By OpenRouter usage, comparable models include DeepSeek V4 Flash, Hy3, and Nemotron 3 Ultra. Side-by-side comparisons are linked in the alternatives table.
Alerts

Track GPT-4o

Email me when GPT-4o's price moves or it gets deprecated.

price moves, plan changes, and the weekly tape. no spam.