NanoGPT
Llama 3.1 405B
Llama 3.1 405B hosted by IONOS in Berlin, Germany. Zero data retention.
meta-llama/llama-3.1-405b-instructContext
131.1K
Max output
8.2K
Input $/M
$2.03
Output $/M
$2.03
Cache read $/M
—
Cache write $/M
—
Against the catalogue
Context window131.1K
Larger than 26% of the 7,784 models listed
Input price$2.03
Cheaper than 17% of priced models
Capabilities
Reasoningnot supported
Tool callingsupported
Structured outputnot supported
Attachmentsnot supported
Temperaturenot supported
Open weightssupported
Interleaved thinkingnot supported
Modalities
Input
Text
Output
Text
Pricing detail
| Rate | Base $/M |
|---|---|
| Input | $2.03 |
| Output | $2.03 |