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.
Model details →NousResearch: Hermes 2 Pro - Llama-3 8B vs Anthropic Claude Haiku Latest
Anthropic Claude Haiku Latest wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.
This model always redirects to the latest model in the Anthropic Claude Haiku family.
Model details →Side-by-side comparison
| Capability | NousResearch: Hermes 2 Pro - Llama-3 8B | Anthropic Claude Haiku Latest | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 8K | 200K | 🏆 Anthropic Claude Haiku Latest |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.14 | $1.00 | 🏆 NousResearch: Hermes 2 Pro - Llama-3 8B |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.14 | $5.00 | 🏆 NousResearch: Hermes 2 Pro - Llama-3 8B |
| Tool / function calling First-class support for emitting structured tool calls. | — | Yes | 🏆 Anthropic Claude Haiku Latest |
| Vision input Accepts image inputs alongside text. | — | Yes | 🏆 Anthropic Claude Haiku Latest |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | Yes | 🏆 Anthropic Claude Haiku Latest |
Frequently asked questions
Is NousResearch: Hermes 2 Pro - Llama-3 8B better than Anthropic Claude Haiku Latest?
Anthropic Claude Haiku Latest wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between NousResearch: Hermes 2 Pro - Llama-3 8B and Anthropic Claude Haiku Latest?
Input: $0.14 vs $1.00 per 1M tokens. Output: $0.14 vs $5.00 per 1M tokens.
What context windows do NousResearch: Hermes 2 Pro - Llama-3 8B and Anthropic Claude Haiku Latest support?
NousResearch: Hermes 2 Pro - Llama-3 8B supports up to 8K tokens. Anthropic Claude Haiku Latest supports up to 200K tokens.
Do both NousResearch: Hermes 2 Pro - Llama-3 8B and Anthropic Claude Haiku Latest support tool calling?
NousResearch: Hermes 2 Pro - Llama-3 8B: not advertised. Anthropic Claude Haiku Latest: yes.
Compare NousResearch: Hermes 2 Pro - Llama-3 8B with other models
vs Anthropic Claude Haiku Latestvs Anthropic Claude Sonnet Latestvs Anthropic: Claude Fable Latestvs Anthropic: Claude Opus Latest