nousresearch familyActive
Nous: Hermes 3 405B Instruct
Open Llama instruction model for multilingual chat, reasoning, and coding
Context
131,072
Max output
16,384
Input / 1M
$1.00
Output / 1M
$1.00
Providers
3
01Profile
Profile
Released
2024-08-16
Last updated
2026-06-11
Knowledge cutoff
—
Weights
Closed
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
No
Tool calling
No
Structured output
Yes
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 3 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2024-08-16
2026-07-20Removedopenrouterofferingremoved→ new
2026-06-10ContextveniceContext window128,000→ new
2026-06-10ContextveniceContext window—→ 128,000
2026-06-10ContextveniceMax output16,384→ new
2026-06-10ContextveniceMax output—→ 16,384
2026-05-15Addedopenrouteroffering→ new
2026-03-15Removedkiloofferingremoved→ new
2026-03-12ContextveniceMax output32,000→ 16,384
2026-02-16Addedkilooffering→ new
2026-02-16Addedkilooffering→ new
2026-01-31Addedopenrouteroffering→ new
2026-01-28ContextveniceContext window131,072→ 128,000