Compare Hermes 4 405B from Nous Research and GPT-5.1-Codex-Mini from OpenAI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
Hermes 4 405B and GPT-5.1-Codex-Mini are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
Hermes 4 405B, from Nous Research, has a 131,072-token context window and is priced at $1/M tokens input, $3/M tokens output on OpenRouter.
GPT-5.1-Codex-Mini, from OpenAI, has a 400,000-token context window and is priced at $0.25/M tokens input, $2/M tokens output on OpenRouter.
| Attribute | Hermes 4 405B | GPT-5.1-Codex-Mini |
|---|---|---|
| Input price | $1/M tokens | $0.25/M tokens |
| Output price | $3/M tokens | $2/M tokens |
| Context window | 131,072 tokens | 400,000 tokens |
| Intelligence Index | 7.4 | 20.4 |
| Coding Index | Not available | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | 0.40 s | 3.25 s |
| Throughput (p50) | 39.0 tok/s | 59.0 tok/s |
Benchmark data updated
GPT-5.1-Codex-Mini is cheaper than Hermes 4 405B on OpenRouter: GPT-5.1-Codex-Mini costs $0.25/M tokens input and $2/M tokens output, while Hermes 4 405B costs $1/M tokens input and $3/M tokens output.
GPT-5.1-Codex-Mini has the longer context window at 400,000 tokens, compared with 131,072 tokens for Hermes 4 405B.
GPT-5.1-Codex-Mini is faster on OpenRouter, generating a median 59.0 tokens per second compared with 39.0 tokens per second for Hermes 4 405B.