☁️ Cloud Benchmarks ☁️
I run cron jobs to periodically test the token generation speed of different cloud LLM providers. The chart helps visualize the distributions of different speeds, as they can vary somewhat depending on the loads. For readability not all models are shown, but you can see the full results in the table below.
Every provider and model now has a dedicated landing page with narrative insights, SEO-friendly metadata, and structured data for search engines. Click any provider or model in the table to explore performance in depth.
I am working daily to add more providers and models, looking anywhere that does not require purchasing dedicated endpoints for hosting (why some models may appear to be missing). If you have any more suggestions let me know on GitHub!! 😊
Pick A Path In 10 Seconds
Quick recommendations from the latest 7-day benchmark slice. Use one path, jump into full results, then drill into provider/model pages.
Loading 7-day recommendations…
Fastest Models Right Now (updated <24h)
| # | Model | Provider | Speed |
|---|---|---|---|
| 1 | llama-3.1-8b | groq | 313 tok/s |
| 2 | qwen-3-32b | groq | 219 tok/s |
| 3 | llama-3.3-70b | groq | 198 tok/s |
| 4 | llama-4-scout | groq | 197 tok/s |
| 5 | llama-3.1-8b | cerebras | 179 tok/s |
📊 Speed Distribution 📊
📚 Full Results 📚
Showing 80 of 80 modelsFlagged statuses: likely_deprecated, deprecated, failing, stale, never_succeeded, disabled
| Status | |||||||
|---|---|---|---|---|---|---|---|
| groq | llama-3.1-8b | Active | 34m ago | 313.00 | 87 | 471 | 90.00 |
| cerebras | qwen-3-32b | Active | 27d ago | 292.00 | 189 | 406 | 200.00 |
| groq | qwen-3-32b | Active | 34m ago | 219.00 | 2 | 374 | 310.00 |
| groq | llama-4-maverick | Active | 6d ago | 203.00 | 1 | 307 | 650.00 |
| groq | llama-3.3-70b | Active | 34m ago | 198.00 | 68 | 340 | 130.00 |
| groq | llama-4-scout | Active | 34m ago | 197.00 | 38 | 335 | 240.00 |
| cerebras | gpt-oss-120b | Active | 3d ago | 188.00 | 1 | 380 | 1120.00 |
| cerebras | llama-3.3-70b | Active | 27d ago | 188.00 | 35 | 256 | 400.00 |
| cerebras | llama-3.1-8b | Active | 36m ago | 179.00 | 1 | 353 | 1260.00 |
| together | llama-3.1-8b | Active | 1d ago | 141.00 | 3 | 228 | 350.00 |
| groq | kimi-k2 | Active | 34m ago | 139.00 | 12 | 215 | 310.00 |
| bedrock | nova-micro | Active | 23m ago | 121.00 | 65 | 152 | 270.00 |
| openai | o3 Mini | Never Succeeded(Medium) | 34m ago | 110.00 | 8 | 164 | 0.00 |
| bedrock | llama-4-maverick | Active | 23m ago | 108.00 | 3 | 139 | 270.00 |
| bedrock | nova-lite | Active | 23m ago | 101.00 | 39 | 132 | 300.00 |
| bedrock | llama-4-scout | Active | 23m ago | 101.00 | 6 | 127 | 280.00 |
| bedrock | llama-3.3-70b | Active | 23m ago | 97.20 | 3 | 136 | 290.00 |
| together | qwen-2.5-7b | Active | 32m ago | 91.60 | 1 | 145 | 510.00 |
| bedrock | nova-pro | Active | 23m ago | 87.80 | 36 | 121 | 360.00 |
| openai | GPT-5.1-codex-max | Active | 34m ago | 82.40 | 11 | 118 | 1320.00 |
| deepinfra | mistral-7b | Stale(Medium) | 36m ago | 77.70 | 5 | 148 | 630.00 |
| openai | gpt-3.5-turbo | Active | 33m ago | 76.30 | 13 | 126 | 500.00 |
| together | llama-3.1-70b | Active | 18d ago | 73.90 | 15 | 129 | 320.00 |
| gemini-2.5-flash-lite | Active | 32m ago | 72.70 | 10 | 132 | 550.00 | |
| openai | gpt-4.1-nano | Active | 34m ago | 71.70 | 9 | 149 | 470.00 |
| deepinfra | devstral-small | Never Succeeded(Medium) | 3h ago | 71.30 | 9 | 140 | 620.00 |
| together | mistral-7b | Active | 18d ago | 70.30 | 2 | 91 | 440.00 |
| openai | gpt-4o | Active | 33m ago | 69.50 | 13 | 173 | 1310.00 |
| fireworks | mixtral-8x22b | Active | 34m ago | 68.90 | 29 | 111 | 410.00 |
| gemini-2.5-flash | Never Succeeded(Medium) | 32m ago | 67.00 | 5 | 105 | 970.00 | |
| together | mixtral-8x7b | Active | 32m ago | 61.20 | 14 | 114 | 160.00 |
| together | llama-3.2-3b | Active | 9d ago | 57.50 | 5 | 121 | 1440.00 |
| deepinfra | mixtral-8x22b | Stale(Medium) | 25d ago | 56.80 | 14 | 66 | 530.00 |
| fireworks | llama-3.3-70b | Active | 34m ago | 54.90 | 1 | 108 | 1670.00 |
| together | llama-3.3-70b | Active | 32m ago | 53.20 | 1 | 146 | 1250.00 |
| anthropic | claude-haiku-4.5 | Active | 36m ago | 51.90 | 19 | 74 | 530.00 |
| openai | gpt-4.1-mini | Active | 34m ago | 51.90 | 15 | 109 | 440.00 |
| together | deepseek-r1 | Active | 32m ago | 51.80 | 1 | 113 | 740.00 |
| openai | o4 Mini | Never Succeeded(Medium) | 34m ago | 49.60 | 4 | 76 | 0.00 |
| bedrock | llama-3.2-90b | Active | 23m ago | 46.80 | 2 | 51 | 370.00 |
| deepinfra | llama-3-8b | Stale(Medium) | 34m ago | 45.60 | 18 | 71 | 320.00 |
| deepinfra | llama-3.1-8b | Stale(Medium) | 35m ago | 44.90 | 3 | 85 | 680.00 |
| deepinfra | llama-3.2-1b | Stale(Medium) | 35m ago | 41.60 | 1 | 100 | 810.00 |
| gemini-2.5-pro | Never Succeeded(Medium) | 32m ago | 41.20 | 2 | 72 | 1680.00 | |
| bedrock | mistral-large | Active | 23m ago | 40.90 | 2 | 47 | 550.00 |
| openai | gpt-4.1 | Active | 34m ago | 40.90 | 10 | 83 | 500.00 |
| deepinfra | llama-3.2-3b | Stale(Medium) | 35m ago | 40.60 | 2 | 99 | 770.00 |
| openai | gpt-4o-mini | Active | 33m ago | 39.80 | 7 | 64 | 390.00 |
| bedrock | claude-haiku-4.5 | Active | 23m ago | 39.40 | 3 | 62 | 1190.00 |
| deepinfra | llama-3.2-90b | Stale(Medium) | 36m ago | 35.50 | 3 | 82 | 730.00 |
| deepinfra | llama-2-70b | Stale(Medium) | 34m ago | 34.60 | 3 | 57 | 610.00 |
| deepinfra | llama-3-70b | Stale(Medium) | 34m ago | 33.60 | 2 | 55 | 660.00 |
| deepinfra | qwen-2.5-72b | Stale(Medium) | 36m ago | 33.00 | 1 | 50 | 790.00 |
| bedrock | claude-3-5-sonnet | Active | 23m ago | 32.80 | 2 | 46 | 650.00 |
| bedrock | claude-3-7-sonnet | Active | 23m ago | 32.70 | 2 | 43 | 750.00 |
| openai | gpt-4-turbo | Active | 33m ago | 32.40 | 2 | 52 | 530.00 |
| bedrock | claude-3-5-haiku | Active | 23m ago | 31.60 | 9 | 38 | 650.00 |
| deepinfra | Qwen 2.5 Coder 32B | Never Succeeded(Medium) | 36m ago | 30.50 | 1 | 82 | 3540.00 |
| openai | GPT-5.1 | Active | 34m ago | 29.50 | 2 | 57 | 1100.00 |
| openai | GPT-5.4 | Active | 34m ago | 27.90 | 19 | 36 | 1080.00 |
| openai | gpt-4 | Active | 33m ago | 27.50 | 5 | 47 | 640.00 |
| openai | GPT-5.2 | Active | 34m ago | 27.00 | 4 | 40 | 970.00 |
| openai | GPT-5.1-codex | Active | 34m ago | 26.20 | 1 | 48 | 1250.00 |
| deepinfra | llama-3.1-405b | Stale(Medium) | 35m ago | 25.60 | 1 | 39 | 760.00 |
| openai | GPT-5.1-codex-mini | Active | 34m ago | 25.50 | 1 | 55 | 1190.00 |
| deepinfra | llama-3.1-70b | Stale(Medium) | 35m ago | 22.90 | 1 | 44 | 1110.00 |
| bedrock | claude-sonnet-4.5 | Active | 23m ago | 22.10 | 2 | 28 | 1690.00 |
| openai | GPT-5.3-codex | Active | 34m ago | 21.30 | 7 | 32 | 1230.00 |
| anthropic | claude-opus-4.5 | Active | 36m ago | 20.60 | 2 | 33 | 1800.00 |
| anthropic | claude-4-sonnet | Active | 36m ago | 20.10 | 6 | 31 | 1770.00 |
| bedrock | claude-3-opus | Active | 24d ago | 19.60 | 8 | 22 | 840.00 |
| bedrock | claude-opus-4.5 | Active | 23m ago | 18.90 | 1 | 27 | 2000.00 |
| deepinfra | llama-3.3-70b | Never Succeeded(Medium) | 36m ago | 17.90 | 1 | 46 | 2670.00 |
| anthropic | Claude Opus 4.1 | Active | 36m ago | 17.60 | 7 | 27 | 1560.00 |
| anthropic | claude-4-opus | Active | 36m ago | 17.40 | 5 | 22 | 1320.00 |
| openai | gpt-5.2-codex | Active | 34m ago | 13.40 | 1 | 27 | 1740.00 |
| openai | o1-pro | Likely Deprecated(Medium) | 34m ago | 9.64 | 1 | 18 | 670.00 |
| deepinfra | llama-3.2-11b | Stale(Medium) | 36m ago | 8.97 | 1 | 61 | 2630.00 |
| openai | GPT-5.2-pro | Active | 34m ago | 8.58 | 4 | 14 | 4890.00 |
| deepinfra | qwen-3-235b | Never Succeeded(Medium) | 36m ago | 8.35 | 1 | 53 | 6610.00 |
Lifecycle snapshot
Loading status summary…