Hermes 2 Pro Llama 3 8B
Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
- Input / output price
- $0.14 / $0.14 per 1M
- Context
- 8K tokens
- Released
- May 1, 2024
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Novita novita/hermes-2-pro-llama-3-8b | $0.14/M | $0.14/M |
Pricing
USD per 1M tokens on Novita, after gateway discounts.
- Input
- $0.14 per 1M
- Output
- $0.14 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Benchmarks
6 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Function calling eval (Fireworks.AI)huggingface.co | 90% | huggingface.co | Sep 14, 2024 |
| Structured JSON output evalhuggingface.co | 84% | huggingface.co | Sep 14, 2024 |
| GPT4All (average)huggingface.co | 72.6% | huggingface.co | Sep 14, 2024 |
| TruthfulQA mc2huggingface.co | 57.8% | huggingface.co | Sep 14, 2024 |
| BigBench (average)huggingface.co | 43.5% | huggingface.co | Sep 14, 2024 |
| AGIEval (average)huggingface.co | 42.4% | huggingface.co | Sep 14, 2024 |
Apps
Use Hermes 2 Pro Llama 3 8B in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Hermes 2 Pro Llama 3 8B FAQ
Short answers, built from the data on this page.
Hermes 2 Pro Llama 3 8B is a model from Nous Research, released on May 1, 2024. Hermes 2 Pro is an upgraded, retrained version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house.
On the Respan gateway, Hermes 2 Pro Llama 3 8B costs $0.14 per 1M input tokens and $0.14 per 1M output tokens on Novita, after gateway discounts.
Hermes 2 Pro Llama 3 8B is served by Novita.
Hermes 2 Pro Llama 3 8B accepts up to 8K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "hermes-2-pro-llama-3-8b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Hermes 2 Pro Llama 3 8B has 6 published benchmark scores, including Function calling eval (Fireworks.AI) 90%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.