Compare Gemini 3.8 Flash from Google and GPT-6 Astra 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.
| Attribute | Gemini 3.8 Flash | GPT-6 Astra |
|---|---|---|
| Input price | $0.75/M tokens | $10/M tokens |
| Output price | $3.75/M tokens | $50/M tokens |
| Context window | 1,048,576 tokens | 1,050,000 tokens |
| Intelligence Index | 30.8 | 56.9 |
| Coding Index | 76.3 | 76.9 |
| Agentic Index | 40.2 | 51.0 |
| Latency (p50) | 2.79 s | 1.34 s |
| Throughput (p50) | 73.0 tok/s | 55.0 tok/s |
| Provided by | OpenAI | |
| Model page | Gemini 3.8 Flash model details, providers and pricing | GPT-6 Astra model details, providers and pricing |
Benchmark data updated
GPT-6 Astra has the longer context window at 1,050,000 tokens, compared with 1,048,576 tokens for Gemini 3.8 Flash.
Gemini 3.8 Flash is faster on OpenRouter, generating a median 73.0 tokens per second compared with 55.0 tokens per second for GPT-6 Astra.
GPT-6 Astra scores higher on coding, with an Artificial Analysis Coding Index of 76.9 compared with 76.3 for Gemini 3.8 Flash.