Compare UI-TARS 7B from bytedance and Step 3.7 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.
UI-TARS 7B and Step 3.7 Flash are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.
UI-TARS 7B , from bytedance, has a 128,000-token context window and is priced at $0.10/M tokens input, $0.20/M tokens output on OpenRouter.
Step 3.7 Flash, from stepfun, has a 262,144-token context window and is priced at $0.20/M tokens input, $1.15/M tokens output on OpenRouter.
| Attribute | UI-TARS 7B | Step 3.7 Flash |
|---|---|---|
| Input price | $0.10/M tokens | $0.20/M tokens |
| Output price | $0.20/M tokens | $1.15/M tokens |
| Context window | 128,000 tokens | 262,144 tokens |
| Intelligence Index | Not available | 19.5 |
| Coding Index | Not available | 39.6 |
| Agentic Index | Not available | Not available |
| Latency (p50) | 0.73 s | 3.17 s |
| Throughput (p50) | 43.0 tok/s | 40.0 tok/s |
Benchmark data updated
UI-TARS 7B is cheaper than Step 3.7 Flash on OpenRouter: UI-TARS 7B costs $0.10/M tokens input and $0.20/M tokens output, while Step 3.7 Flash costs $0.20/M tokens input and $1.15/M tokens output.
Step 3.7 Flash has the longer context window at 262,144 tokens, compared with 128,000 tokens for UI-TARS 7B .
UI-TARS 7B is faster on OpenRouter, generating a median 43.0 tokens per second compared with 40.0 tokens per second for Step 3.7 Flash.