Hermes 3 405B Instruct
Nous ResearchReleased Aug 16, 2024Open weights · Llama Community Licensehermes-3-llama-3.1-405b
- Reasoning
- no
- Knowledge cutoff
- December 2024
- Context
- 131K tokens
- Max output
- 16k tokens
- Input
- text
- API features
- structured outputs, JSON mode, seed
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Nous Research · cutoff: llama.com
Its only host, DeepInfra, serves fp8 weights (maker: bf16). Weights and context per host
Open weights under Llama Community License: you can run Hermes 3 405B Instruct on your own hardware instead of paying per token.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| DeepInfrafp8 (bf16) · 128K ctx · 16K out | $1.00 | $1.00 | — | 25 | 0.29 s | 100% | Oct 23 |
1 provider · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| DeepInfra | fp8 | 128K | 16K | no | yes | no |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
Hermes 3 405B Instruct spec sheet, field by field, with sources
Hermes 3 405B Instruct spec sheetmaker-declared
What Nous Research declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- 131,072 tokens
- Parameters
- 405,853,388,800≈ 405.9B
- Active experts
- none declared in the weights
- Weight precision
- bfloat16
- License
- Llama Community License — open weights, conditionalcuratedScope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- December 2024maker's docs
- Modalities
- text
- Max output (official)
- to verify
- Release date
- to verify≈ August 16, 2024 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
Also declared in the weights
- Architecture class
- LlamaForCausalLM
- Layers
- 126
- Vocabulary
- 128,256 tokens
- Weights first published
- August 13, 2024
- Weights last updated
- October 8, 2024
- Languages declared
- English
- Paper
- arXiv:2408.11857
NousResearch/Hermes-3-Llama-3.1-405B · config.json @ b9fe8ed · read 2026-10-08 · 6 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| DeepInfra | $1.50 | $8.50 | $5.00 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other Nous Research models · all its models, hosts and history ›
- Hermes 3 70B Instruct1 provider · from $1.40
- Hermes 4 405B1 provider · from $4.00