openai / text-generation API-only released 2024-05-13

GPT-4o

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...

Input / 1M
$2.50
Output / 1M
$10.00
Context
128K
AA Intelligence
—
Closed weights — available only as a hosted API text + image + file → text Knowledge cutoff Oct 2023 View on OpenRouter ↗

Pricing

via OpenRouter · USD per 1M tokens · synced 2026-10-24
$2.50
input / 1M
$10.00
output / 1M
$1.25
cached input / 1M
$12.50
1M in + 1M out
:batch variant $1.25 in · $5.00 out
Context window
128,000 tokens
Max output
16,384 tokens
Providers
2
Cheapest provider
Azure · $2.50 / $10.00
Best throughput
—
AA Intelligence / Coding / Agentic
— / — / —
✓ Tool calling ✗ Reasoning ✓ Structured outputs ✓ Image input ✓ File input ✗ Audio input ✓ Prompt caching

Price history

tracking started — chart appears after 7 days of snapshots (6 recorded)
Current: $2.50 input · $10.00 output per 1M tokens

Benchmarks

Third-party indices as published through OpenRouter — Artificial Analysis and Design Arena. Not measured by us.

AA Intelligence Index
—
AA Coding Index
—
AA Agentic Index
—
Design Arena
CategoryEloWin %Rank
3d 869 39.2% #122
codecategories 861 34.8% #136
dataviz 858 36% #131
gamedev 906 42.3% #135
uicomponent 883 38.1% #131
website 831 31.5% #145

Providers

2 providers · per 1M tokens · last 30 min metrics
ProviderQuantContextInputOutputUptimeTok/s
Azure unknown 128K $2.50 $10.00 100% —
OpenAI unknown 128K $2.50 $10.00 100% —
Provider data from OpenRouter's endpoint listing, refreshed daily.

Specifications

Organisation
openai
Released on OpenRouter
2024-05-13
Context window
128,000 tokens
Max output
16,384 tokens
Input
text, image, file
Output
text
Knowledge cutoff
October 2023
Tokenizer
GPT
Moderated by provider
Yes
OpenRouter id
openai/gpt-4o
Compare with
Prices, context and providers from the public OpenRouter API, snapshotted daily; benchmark indices from Artificial Analysis. See /methodology.