Cheaper Inference
Model record / Venice AI
gpt-image-2
Access gpt-image-2 from Venice AI through one OpenAI-compatible API with live market-linked pricing and usage-based billing.
Image generationText inputImage editingStandard generationNon-streaming15% below list
What you pay
Current catalog rates.
Input / image—
Output / image—
Current discount15%
Observed reliability
94.5
Successful provider-reaching requests
Output speed
—
Median tokens per second over sustained generations
TTFT
—
p50 · p90 not available · n 0
Latency
43.2 s
p50 · p90 66.8 s · n 1,426
Evidence strength
—
At a glance
- Provider
- Venice AI
- Model ID
- gpt-image-2
- Type
- Image generation
- Endpoint
- /v1/images/generations
- Input
- text
- Output
- image
- Vision input
- Not supported
- Image editing
- Supported
- Video input
- Not supported
- Reasoning
- Not supported
- Streaming
- Not supported
- Context window
- 128,000 tokens
Parameters by endpoint
The request field of each parameter on each endpoint, and the values it takes.
This model takes the fields in its sample request. It has no other stated parameters.
Pricing history
See how much this model saves and when its recorded price has been lowest.
Time zone
gpt-image-2
Growing confidenceThis model averaged 15.0% below comparable direct provider prices across the selected range. Its strongest observed window was Any observed hour in UTC.
Last 24 hours
Average saved
15.0%
Last 24 hours
Cheapest time
Any observed hour
15.0% average savings
Hourly coverage
24/24
24 total observations
Signal quality
Growing
Ready for planning
Typical unit savings$0.75 / 1M input tokens$4.50 / 1M output tokens
When this model is cheapest
Each bar is the average discount for that hour in UTC (UTC). Missing bars mean no observation was recorded.
ObservedCheapestNo data
Hover a bar for savings per token and observation counts.
Source buckets are UTC; labels are converted to UTC.
Last 24 hours
#111
of 423 ranked models
Last 7 days
#134
of 437 ranked models
Last 30 days
#111
of 437 ranked models
Ready when you are
Stop paying list price for tokens.
Marketplace pricing, capped at list, optimized further.