Compare Gemini Omni 1.2 Flash from Google and Moondream 3.1 from Moondream on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
| Attribute | Gemini Omni 1.2 Flash | Moondream 3.1 |
|---|---|---|
| Input price | $1.50/M tokens | $0.30/M tokens |
| Output price | $9/M tokens | $2.50/M tokens |
| Context window | 131,072 tokens | 32,000 tokens |
| Intelligence Index | Not available | Not available |
| Coding Index | Not available | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | 1.90 s | 0.18 s |
| Throughput (p50) | 167.0 tok/s | 129.0 tok/s |
| Provided by | Moondream | |
| Model page | Gemini Omni 1.2 Flash model details, providers and pricing | Moondream 3.1 model details, providers and pricing |
Moondream 3.1 is cheaper than Gemini Omni 1.2 Flash on OpenRouter: Moondream 3.1 costs $0.30/M tokens input and $2.50/M tokens output, while Gemini Omni 1.2 Flash costs $1.50/M tokens input and $9/M tokens output.
Gemini Omni 1.2 Flash has the longer context window at 131,072 tokens, compared with 32,000 tokens for Moondream 3.1.
Gemini Omni 1.2 Flash is faster on OpenRouter, generating a median 167.0 tokens per second compared with 129.0 tokens per second for Moondream 3.1.