Prime Inference
Gemini 4 Neon
Google's Gemini 4 model for fast, frontier-level coding, knowledge work and science workflows, with four thinking levels and a 1M-token context window
google/gemini-4-neonContext
1M
Max output
943.7K
Input $/M
$3.00
Output $/M
$15.00
Cache read $/M
—
Cache write $/M
—
Against the catalogue
Context window1M
Larger than 92% of the 10,022 models listed
Input price$3.00
Cheaper than 12% of priced models
Capabilities
Reasoningsupported
Tool callingsupported
Structured outputsupported
Attachmentssupported
Temperaturesupported
Open weightsnot supported
Interleaved thinkingnot supported
Modalities
Input
AudioImageTextVideo
Output
Text
Reasoning controls
effortlow, medium, high, xhighPricing detail
| Rate | Base $/M |
|---|---|
| Input | $3.00 |
| Output | $15.00 |