⏱ Capsule Public Content Creation
Moon Astronaut — Photorealism & Prompt Fidelity Test
Ezarwebmaster· Jun 29, 2026
Locked Reference Prompt
IMMUTABLEScientific timeline lock active
A lonely astronaut sitting on the surface of the Moon,
looking at Earth in the distance. Photorealistic.
Golden hour lighting. Wide angle shot. No text.
Add a Benchmark Run
Sign in to run this prompt against hundreds of models with your own OpenRouter key and archive the results.
Timeline (8 runs)
Run Activity
8 runs in the last 6 months
Jan
Feb
Mar
Apr
May
Jun
Jul
LessMore
Cost vs Speed
size = output tokens · top-left is best
size = tokens
value frontier — no model is faster & cheaper Capsule Stats
Runs
8
Total cost
$0.6704
Tokens
24k
Avg latency
6.00 s
Models
8
Web Searches
0
Fastest 
openai/gpt-5.4-image-2-20260421411 ms
openai/gpt-5.4-image-2-20260421411 ms Cheapest 
google/gemini-3.1-flash-lite-image-20260630$0.0336
google/gemini-3.1-flash-lite-image-20260630$0.0336 Top provider Google DeepMind×4
Google DeepMind×4 145 reasoning last 9d ago
Tip: Select 2 or more runs via their "Compare" buttons — or filter by company below and compare them all at once — then open the Compare Studio: verdicts, benchmark bars, charts, side-by-side reading and response diff.
⏱
Benchmark Run — Jul 3, 2026 Latest
Google DeepMindgemini-3.1-flash-lite-image-20260630
stop
Latency
2.67 s
client → response
Input Tokens
36
prompt tokens
Output
1,120
generated
Total Tokens
1,156
in + out
Billed Cost
$0.0336
OR Credits
Reasoning
—
thinking tokens
Generated Image
Remote Storage
Researcher Notes
⏱
Benchmark Run — Jun 29, 2026
Google DeepMindgemini-3-pro-image-20260528
stop
Latency
2.83 s
client → response
Input Tokens
37
prompt tokens
Output
1,387
generated
Total Tokens
1,424
in + out
Billed Cost
$0.1362
OR Credits
Reasoning
145
thinking tokens
Generated Image
Remote Storage
Researcher Notes
⏱
Benchmark Run — Jun 29, 2026
Google DeepMindgemini-3.1-flash-image-20260528
stop
Latency
10.06 s
client → response
Input Tokens
37
prompt tokens
Output
1,593
generated
Total Tokens
1,630
in + out
Billed Cost
$0.0686
OR Credits
Reasoning
—
thinking tokens
Generated Image
Remote Storage
Researcher Notes
⏱
Benchmark Run — Jun 29, 2026
Black Forest Labsflux.2-max
stop
Latency
10.10 s
client → response
Input Tokens
40
prompt tokens
Output
4,096
generated
Total Tokens
4,136
in + out
Billed Cost
$0.0700
OR Credits
Reasoning
—
thinking tokens
Generated Image
1.4 MB
Researcher Notes
⏱
Benchmark Run — Jun 29, 2026
xAI (Grok)grok-imagine-image-quality-20260512
stop
Latency
5.37 s
client → response
Input Tokens
40
prompt tokens
Output
4,175
generated
Total Tokens
4,215
in + out
Billed Cost
$0.0500
OR Credits
Reasoning
—
thinking tokens
Generated Image
Remote Storage
Researcher Notes
⏱
Benchmark Run — Jun 29, 2026
Microsoftmai-image-2.5
stop
Latency
10.12 s
client → response
Input Tokens
42
prompt tokens
Output
1,024
generated
Total Tokens
1,066
in + out
Billed Cost
$0.0483
OR Credits
Reasoning
—
thinking tokens
Generated Image
Remote Storage
Researcher Notes
⏱
Benchmark Run — Jun 29, 2026
OpenAIgpt-5.4-image-2-20260421
stop
Latency
411 ms
client → response
Input Tokens
1,673
prompt tokens
Output
7,077
generated
Total Tokens
8,750
in + out
Billed Cost
$0.2249
OR Credits
Reasoning
—
thinking tokens
Generated Image
Remote Storage
Researcher Notes
⏱
Benchmark Run — Jun 29, 2026
Google DeepMindgemini-2.5-flash-image
stop
Latency
6.46 s
client → response
Input Tokens
36
prompt tokens
Output
1,290
generated
Total Tokens
1,326
in + out
Billed Cost
$0.0387
OR Credits
Reasoning
—
thinking tokens
Generated Image
Remote Storage