Compare gpt-oss-120b from OpenAI and Cydonia 24B V4.1 from Drummer on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
gpt-oss-120b and Cydonia 24B V4.1 are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
gpt-oss-120b, from OpenAI, has a 131,072-token context window and is priced at $0.03/M tokens input, $0.17/M tokens output on OpenRouter.
Cydonia 24B V4.1, from Drummer, has a 131,072-token context window and is priced at $0.30/M tokens input, $0.50/M tokens output on OpenRouter.
| gpt-oss-120b | Cydonia 24B V4.1 | |
|---|---|---|
| Input price | $0.03/M tokens | $0.30/M tokens |
| Output price | $0.17/M tokens | $0.50/M tokens |
| Context window | 131,072 tokens | 131,072 tokens |
| Intelligence Index | 11.6 | Not available |
| Coding Index | 30.4 | Not available |
| Agentic Index | 3.7 | Not available |
| Latency (p50) | 0.45 s | 0.61 s |
| Throughput (p50) | 30.0 tok/s | 49.0 tok/s |
gpt-oss-120b is cheaper than Cydonia 24B V4.1 on OpenRouter: gpt-oss-120b costs $0.03/M tokens input and $0.17/M tokens output, while Cydonia 24B V4.1 costs $0.30/M tokens input and $0.50/M tokens output.
gpt-oss-120b and Cydonia 24B V4.1 have the same context window of 131,072 tokens.
Cydonia 24B V4.1 is faster on OpenRouter, generating a median 49.0 tokens per second compared with 30.0 tokens per second for gpt-oss-120b.