openrouter Provider Benchmarks

Comprehensive performance summary covering 46 models.

This provider hub highlights throughput and latency trends across every openrouter model monitored by LLM Benchmarks. Use it to compare hosting tiers, track regressions, and discover the fastest variants in the catalogue.


Provider Snapshot

Models Tracked

46

Median Tokens / Second

43.78

Median Time to First Token (ms)

0.81

Last Updated

Dec 24, 2025

Key Takeaways

  • 46 openrouter models are actively benchmarked with 44111 total measurements across 43144 benchmark runs.

  • llama-3.2-1b leads the fleet with 111.00 tokens/second, while codestral delivers 70.10 tok/s.

  • Performance varies by 58.3% across the openrouter model lineup, indicating diverse optimization strategies for different use cases.

  • Median time to first token across the fleet is 0.81 ms, showing excellent responsiveness for interactive applications.

  • The openrouter model fleet shows varied performance characteristics (42.9% variation coefficient), reflecting diverse model architectures.

Fastest Models

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
openrouterllama-3.2-1b111.0028.00159.000.37
openroutermistral-7b86.101.70156.000.30
openrouterministral-3b83.305.66114.000.37
openroutermistral-saba80.306.79124.000.39
openrouterministral-8b75.004.8489.100.38
openroutercodestral70.1022.1097.100.49

All Models

Complete list of all openrouter models tracked in the benchmark system. Click any model name to view detailed performance data.

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
openrouterqwen-3-30b42.605.11124.000.99
openrouterqwen-3-8b46.001.15135.001.40
openrouterqwen-3-14b32.501.4177.201.32
openrouterqwen-3-32b34.201.96167.001.03
openrouterqwen-3-235b36.001.3091.300.76
openroutergpt-4.136.709.1880.600.21
openroutergpt-4.1-mini39.3012.6085.600.21
openroutergpt-4.1-nano46.201.65103.000.31
openrouterllama-3.1-nemotron-ultra35.108.6938.100.33
openrouterqwen-2.5-vl26.801.0768.901.03
openroutermistral-small35.103.12118.001.09
openrouterqwq-32b13.502.6617.503.02
openroutermistral-saba80.306.79124.000.39
openrouterqwen-vl-plus45.6011.3071.100.82
openrouterqwen-vl-max32.601.4645.000.90
openrouterdeepseek-r138.902.1099.301.04
openroutermistral-large41.501.4454.600.73
openrouterpixtral-large36.701.4455.800.70
openrouterqwen-2.5-coder32.103.5373.500.93
openrouterqwen-2.5-7b47.401.24128.001.09
openrouterllama-3.1-nemotron-70b40.403.1247.100.40
openrouterllama-3.2-3b45.405.45133.000.49
openrouterllama-3.2-1b111.0028.00159.000.37
openrouterllama-3.2-11b28.501.93104.001.17
openrouterllama-3.2-90b42.503.0987.000.41
openrouterqwen-2.5-72b33.802.4972.000.74
openrouterllama-3.1-8b50.104.34271.000.65
openrouterqwen-2.5-vl-7b57.801.5781.700.64
openrouterllama-3.1-70b32.401.35127.000.76
openrouterllama-3.1-405b18.701.1230.101.36
openroutergpt-4o52.203.50112.000.53
openroutermistral-nemo34.907.48121.000.79
openroutergpt-4o-mini39.4010.9087.600.51
openroutermistral-7b86.101.70156.000.30
openrouterllama-3.3-70b34.201.45234.000.77
openrouterdevstral-small39.702.28100.000.41
openroutermistral-medium28.601.0850.301.60
openrouterpixtral-12b57.302.3774.200.55
openrouterdeepseek-chat26.9010.5051.801.38
openroutercodestral70.1022.1097.100.49
openrouterdevstral-medium39.404.4449.800.89
openrouterdeepseek-v319.202.68111.001.33
openroutermagistral-medium30.602.3939.601.24
openroutermagistral-small57.5016.9072.100.49
openrouterministral-8b75.004.8489.100.38
openrouterministral-3b83.305.66114.000.37

Featured Models

Frequently Asked Questions

Based on recent tests, llama-3.2-1b shows the highest average throughput among tracked openrouter models.

This provider summary aggregates 44111 individual prompts measured across 43144 monitoring runs over the past month.