NanoGPT
Agnes 3.0 Flash
Agnes 3.0 Flash is a low-cost model for coding, tool use, and multi-turn agent tasks. It supports text and image input, optional thinking, and a 512K-token context window.
agnes-3.0-flashContext
524.3K
Max output
65.5K
Input $/M
$0.05
Output $/M
$0.15
Cache read $/M
$0.005
Cache write $/M
—
Against the catalogue
Context window524.3K
Larger than 65% of the 7,784 models listed
Input price$0.05
Cheaper than 87% of priced models
Capabilities
Reasoningsupported
Tool callingsupported
Structured outputnot supported
Attachmentssupported
Temperaturenot supported
Open weightsnot supported
Interleaved thinkingnot supported
Modalities
Input
TextImage
Output
Text
Pricing detail
| Rate | Base $/M |
|---|---|
| Input | $0.05 |
| Output | $0.15 |
| Cache read | $0.005 |