Endostatin is a potent endogenous angiogenic inhibitor with implicated antitumor activity. However, efficacy of recombinant human endostatin (rhES) in clinical trials is controversial, and application of rhES in treatment of metastatic melanoma awaits further investigations. This phase II trial evaluated the efficacy and safety of a soluble and stable rhES (Endostar) plus dacarbazine in patients with metastatic melanomas that contains no mutations in c-kit and BRAF genes. A total of 110 patients received placebo plus dacarbazine (250 mg/m², n = 54) or Endostar (7.5 mg/m²) plus dacarbazine (250 mg/m², n = 56). The primary end points were progression-free survival (PFS) and overall survival (OS). Median PFS in the Endostar plus dacarbazine arm was 4.5 months versus 1.5 months in the placebo plus dacarbazine arm (hazard ratio (HR) = 0.578; P = 0.013). There were statistically significant improvements in OS (median, 12.0 months versus 8.0 months; HR, 0.522; P = 0.005) in favor of the Endostar plus dacarbazine arm. The regimen was generally well tolerated and had a manageable toxicity profile. Our trial suggests that Endostar plus dacarbazine is well tolerated in patients with metastatic melanoma harboring no genetic mutations popular for targeted therapy and yields a significant improvement in PFS and OS.