Compare Gemini 3 Flash Preview from Google and Step 3.5 Flash from stepfun on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.
Gemini 3 Flash Preview and Step 3.5 Flash are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
Gemini 3 Flash Preview, from Google, has a 1,048,576-token context window and is priced at $0.50/M tokens input, $3/M tokens output on OpenRouter.
Step 3.5 Flash, from stepfun, has a 262,144-token context window and is priced at $0.10/M tokens input, $0.30/M tokens output on OpenRouter.
| Gemini 3 Flash Preview | Step 3.5 Flash | |
|---|---|---|
| Input price | $0.50/M tokens | $0.10/M tokens |
| Output price | $3/M tokens | $0.30/M tokens |
| Context window | 1,048,576 tokens | 262,144 tokens |
| Intelligence Index | 26.3 | 17.0 |
| Coding Index | Not available | Not available |
| Agentic Index | Not available | Not available |
| Latency (p50) | 2.48 s | 1.34 s |
| Throughput (p50) | 103.0 tok/s | 65.0 tok/s |
Step 3.5 Flash is cheaper than Gemini 3 Flash Preview on OpenRouter: Step 3.5 Flash costs $0.10/M tokens input and $0.30/M tokens output, while Gemini 3 Flash Preview costs $0.50/M tokens input and $3/M tokens output.
Gemini 3 Flash Preview has the longer context window at 1,048,576 tokens, compared with 262,144 tokens for Step 3.5 Flash.
Gemini 3 Flash Preview is faster on OpenRouter, generating a median 103.0 tokens per second compared with 65.0 tokens per second for Step 3.5 Flash.