Models

gpt-4o vs gpt-4o-free

Context lengths are 128,000 tokens on gpt-4o and 1,047,576 tokens on gpt-4o-free. Time to first token (TTFT) measured on AIHubMix is 0.6s on gpt-4o and 0.5s on gpt-4o-free. Measured output throughput is 52.2 tok/s on gpt-4o and 72.3 tok/s on gpt-4o-free. On the LMArena coding leaderboard gpt-4o scores 1360 and gpt-4o-free scores 1360.

OpenAIgpt-4oOpenAIgpt-4o-free
OpenAI logo
gpt-4o
OpenAI · text, image → text

GPT-4o (“o” stands for “omni”) is a new-generation multimodal model designed for more natural human–computer interaction. It can accept any combination of text, audio, image, and video as input, and generate multimodal outputs including text, audio, and images. With audio response latency as low as 232 milliseconds on average around 320 milliseconds, it approaches real human conversational speed. The model delivers strong performance in English text and code, significantly improved multilingual understanding, and outstanding capabilities in visual and audio perception, while offering faster API performance and substantially reduced cost for real-time and complex multimodal applications.

Input$2.50 /M
Output$10.00 /M
OpenAI logo
gpt-4o-free
OpenAI · text, image → text

This free model API comes from the OpenAI model deployed on Azure. To prevent abuse, the external content filter provided by Azure has been enforced, which will result in additional delays. If you want to experience the full version of the model API without filters, please use the paid version and request the model name ID without "-free".

Input$0.00 /M
Output$0.00 /M

Pricing & Specifications

Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.

gpt-4o
gpt-4o-free
Input /M
$2.50
$0.00
Output /M
$10.00
$0.00
Cache read /M
$1.25
$0.00
Context length
128,000
1,047,576
Max output
16,384
32,768
Time to First Token
0.6 s
0.5 s
Throughput
52.2 tok/s
72.3 tok/s
Modalities
textimage
textimage
Supported Parameters
toolsfunction callingstructured outputs
toolsfunction callingstructured outputslong context
API Formats

Promotional prices show the discounted rate; see each model page for promotion windows.

Activity Past 30 Days

Daily traffic served through AIHubMix — how demand for each model is trending.

gpt-4ogpt-4o-free

Tokens / day

-

Requests / day

-

Performance Past 3 Days

Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.

gpt-4ogpt-4o-free

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

LMArena Benchmarks

LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.

Text
gpt-4ogpt-4o-free
128013201360
Overall
13351335
Coding
13601360
Math
13081309
Hard prompts
13271327
Instruction following
13181318
Multi-turn
13261326
Creative writing
13261326
Longer query
13381338
Chinese
13291329
English
13481348
Vision
gpt-4ogpt-4o-free
110011201140
Overall
11191119

Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.

Cost calculator

Estimate your monthly bill for the same workload on each model.

gpt-4o-free
$0.00 /mo
gpt-4o
$300 /mo

Monthly = daily × 30. Discounted rates applied where a promotion is active.

FAQ

How do their coding arena scores compare?

gpt-4o-free: 1360; gpt-4o: 1360 (LMArena coding leaderboard).

Which responds faster?

gpt-4o-free: 0.5s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.

How large is each context window?

gpt-4o accepts 128,000 and gpt-4o-free accepts 1,047,576 input tokens. Maximum output per request is 16,384 tokens on gpt-4o and 32,768 tokens on gpt-4o-free.

Which one generates tokens faster?

gpt-4o-free at 72.3 tok/s and gpt-4o at 52.2 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.

What inputs and capabilities does each model support?

gpt-4o accepts text and image input and supports tool calling, function calling and structured outputs; gpt-4o-free accepts text and image input and supports tool calling, function calling, structured outputs and long context.

Can I call gpt-4o and gpt-4o-free with the same API key?

Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.

Popular comparisons

Related model match-ups readers also look at.