Hermes 3 70B Instruct
by Nous ResearchChat
Open Llama instruction model for multilingual chat, reasoning, and coding
- Context
- 131K tokens
- Max output
- 32,768 tokens
- Parameters
- 70.6B total
- Released
- 2024-08-18
- Weights
- Open
- Licence
- llama3
nousresearch/hermes-3-llama-3-1-70b · also seen as deepinfra/NousResearch/Hermes-3-Llama-3.1-70B
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2024-08-18
- Weights
- Opennot gated
- License
- llama3
- Input
- Text
- Output
- Text
- Context window
- 131,072 max across endpoints
- Max output
- 32,768
- Providers
- 3 + 4 gateways, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.700–$0.963 in · $0.700–$0.963 out per 1M tokens · 2 of 3 providers have a comparable price
More details
- Last updated
- 2024-08-18
- Knowledge cutoff
- 2023-12-31
- Weights link
- Hugging Face · NousResearch/Hermes-3-Llama-3.1-70B
- Parameters
- 70.6B total
- Base model
- meta-llama/Llama-3.1-70B
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel tools
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt cachingunknown
- Web searchunknown
- Computer useunknown
- System messages
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
Atom feedNo change since 19 Oct 2026. The cheapest direct price has been $0.70 in / $0.70 out per 1M tokens at Deep Infra on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Hermes 3 70B Instruct |
|---|---|---|---|---|---|
| Llama Guard 3 8BMeta | $0.408 | $0.484 | $0.03 | 131K | +0% |
| Qwen3-Vl 30b A3b ThinkingAlibaba (Qwen) | $0.408 | $0.29 | $1.00 | 262K | +0% |
| DeepSeek V3DeepSeek | $0.408 | $0.27 | $1.10 | 164K | +0% |
| MiniMax-M2.1MiniMax | $0.408 | $0.27 | $1.10 | 205K | +0% |
| DeepSeek V4 ProDeepSeek | $0.406 | $0.348 | $0.696 | 1M | −0% cheaper |
| GLM-4.6Z.ai (Zhipu AI) | $0.411 | $0.274 | $1.10 | 205K | +1% |
| GLM-4.7Z.ai (Zhipu AI) | $0.411 | $0.274 | $1.10 | 205K | +1% |
| GLM-4.5VZ.ai (Zhipu AI) | $0.411 | $0.274 | $1.10 | 64K | +1% |
More from Nous Research
Newest Nous Research models in the catalogue. All Nous Research models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Hermes-4-405B | 2025-08-26 | 131K | from $1.00 |
| Hermes 3 Llama 3.1 405b | 2024-08-16 | 131K | from $1.00 |
| Hermes 2 Pro Llama 3 8B | 2024-04-30 | 8.2K | from $0.14 |
| nous-hermes-llama2-13b | — | 4.1K | from $0.17 |
| Hermes-4-70B | — | 131K | from $0.13 |
| nous-hermes-2-yi-34b | — | 4.1K | from $0.80 |
| nous-hermes-2-mixtral-8x7b-dpo | — | 32.8K | from $0.50 |
| nous-capybara-7b-v1p9 | — | — | from $0.20 |