Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either respond directly or generate explicit <think>...</think> r…
Model details →Nous: Hermes 4 70B vs OpenAI: gpt-oss-20b
OpenAI: gpt-oss-20b wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deplo…
Model details →Side-by-side comparison
| Capability | Nous: Hermes 4 70B | OpenAI: gpt-oss-20b | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 131K | 131K | Tie |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.13 | $0.03 | 🏆 OpenAI: gpt-oss-20b |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.40 | $0.11 | 🏆 OpenAI: gpt-oss-20b |
| Tool / function calling First-class support for emitting structured tool calls. | — | Yes | 🏆 OpenAI: gpt-oss-20b |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | Yes | Tie |
Frequently asked questions
Is Nous: Hermes 4 70B better than OpenAI: gpt-oss-20b?
OpenAI: gpt-oss-20b wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Nous: Hermes 4 70B and OpenAI: gpt-oss-20b?
Input: $0.13 vs $0.03 per 1M tokens. Output: $0.40 vs $0.11 per 1M tokens.
What context windows do Nous: Hermes 4 70B and OpenAI: gpt-oss-20b support?
Nous: Hermes 4 70B supports up to 131K tokens. OpenAI: gpt-oss-20b supports up to 131K tokens.
Do both Nous: Hermes 4 70B and OpenAI: gpt-oss-20b support tool calling?
Nous: Hermes 4 70B: not advertised. OpenAI: gpt-oss-20b: yes.