Active
hermes-4-405b
Hermes 4 405B is a frontier hybrid-mode reasoning model built on Llama 3.1, optimized for advanced logic, math, coding, and structured output generation.
Context
131,072
Max output
128,000
Input / 1M
$0.30
Output / 1M
$1.20
Providers
5
01Profile
Profile
Released
2024-08-13
Last updated
2026-02-04
Knowledge cutoff
—
Weights
Closed
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
No
Tool calling
Yes
Structured output
Yes
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 6 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2024-08-13
2026-09-02ContextnebiusContext window128,000→ 131,072
2026-08-31Removedllmgatewayofferingremoved→ new
2026-08-31Removedllmgateway-providersofferingremoved→ new
2026-08-25ContextkiloMax output26,215→ 117,964
2026-08-25ContextopenrouterMax output131,072→ 117,964
2026-08-20Addedllmgateway-providersoffering→ new
2026-08-05Addedcortecsoffering→ new
2026-07-23Addedllmgatewayoffering→ new
2026-02-17Addednano-gptoffering→ new
2026-02-17Price cutnano-gptinput / 1M$1.00→ $0.30
2026-02-17Price cutnano-gptoutput / 1M$2.00→ $1.20
2026-02-16Addedkilooffering→ new