LLMHermes 4 Large API pricing uncensored
Hermes 4 Large by NanoGPT costs $0.30 per 1M input tokens and $1.20 per 1M output tokens (1M in + 1M out = $1.50).
- API model id
nousresearch/hermes-4-405b- Input / 1M
- $0.30
- Output / 1M
- $1.20
- Cached input / 1M
- —
- Context window
- 128K
- Uncensored
- Model card: 'neutrally-aligned', 'reduced refusal rates', SOTA on RefusalBench 'without censorship' (Nous Research). Source. Not an endorsement; follow the law and the provider's terms. What counts.
- Notes
- NanoGPT pay-as-you-go list price from its detailed models API (USD per 1M tokens). NanoGPT routes to upstream hosts.
- Source
- https://nano-gpt.com/api/v1/models?detailed=true
- Provider type
- Aggregator (HQ: unknown)
- Regions
- unknown
- EU data residency
- unknown — NanoGPT routes requests to upstream model hosts; it does not publish serving regions or a company address on its privacy page.
- Last verified
- 2026-10-26
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| NanoGPT | Hermes 4 Large | $0.60 |
Uses standard list prices (no caching, batch or off-peak discounts). € and CHF rows are priced in that currency by the provider and not converted, so compare them with care.
Other NanoGPT models
- Venice Uncensored: $0.40 / $1.80
- GLM 5.3 Uncensored: $1.25 / $2.25
- GLM 5.3 Flash Uncensored: $0.20 / $0.80
- Apex Flash 1 Abliterated: $0.15 / $0.50
- Qwen 3.8 27B Uncensored: $1.00 / $3.00
- Qwen 3.8 27B Uncensored Fast by Heabsy: $1.00 / $3.00
- DeepSeek V4.1 Flash Uncensored: $0.33 / $1.32
- MiMo V2.6 Flash Uncensored: $0.50 / $1.50