☁️ 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 | 319 tok/s |
| 2 | qwen-3-32b | groq | 232 tok/s |
| 3 | llama-4-scout | groq | 211 tok/s |
| 4 | llama-3.3-70b | groq | 203 tok/s |
| 5 | llama-3.1-8b | cerebras | 194 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 | 58m ago | 319.00 | 87 | 471 | 90.00 |
| cerebras | qwen-3-32b | Active | 19d ago | 256.00 | 4 | 444 | 400.00 |
| groq | qwen-3-32b | Active | 58m ago | 232.00 | 2 | 391 | 300.00 |
| groq | llama-4-scout | Active | 58m ago | 211.00 | 38 | 335 | 210.00 |
| groq | llama-3.3-70b | Active | 58m ago | 203.00 | 68 | 340 | 130.00 |
| cerebras | llama-3.1-8b | Active | 1h ago | 194.00 | 1 | 348 | 970.00 |
| groq | llama-4-maverick | Active | 58m ago | 194.00 | 1 | 307 | 620.00 |
| cerebras | gpt-oss-120b | Active | 1h ago | 193.00 | 13 | 380 | 800.00 |
| cerebras | llama-3.3-70b | Active | 19d ago | 182.00 | 17 | 316 | 400.00 |
| together | llama-3.1-8b | Active | 57m ago | 142.00 | 3 | 232 | 380.00 |
| groq | kimi-k2 | Active | 58m ago | 141.00 | 12 | 215 | 310.00 |
| bedrock | nova-micro | Active | 8m ago | 122.00 | 65 | 150 | 270.00 |
| openai | o3 Mini | Never Succeeded(Medium) | 58m ago | 111.00 | 21 | 160 | 0.00 |
| bedrock | llama-4-maverick | Active | 8m ago | 108.00 | 3 | 139 | 260.00 |
| bedrock | nova-lite | Active | 8m ago | 102.00 | 39 | 132 | 300.00 |
| bedrock | llama-4-scout | Active | 8m ago | 101.00 | 4 | 129 | 270.00 |
| bedrock | llama-3.3-70b | Active | 8m ago | 98.90 | 3 | 137 | 290.00 |
| together | qwen-2.5-7b | Active | 57m ago | 94.20 | 11 | 145 | 240.00 |
| bedrock | nova-pro | Active | 8m ago | 90.50 | 31 | 121 | 350.00 |
| openai | GPT-5.1-codex-max | Active | 58m ago | 80.10 | 11 | 118 | 1390.00 |
| openai | gpt-3.5-turbo | Active | 57m ago | 78.70 | 13 | 126 | 470.00 |
| gemini-2.5-flash-lite | Active | 57m ago | 75.90 | 10 | 132 | 530.00 | |
| together | llama-3.1-70b | Active | 10d ago | 72.60 | 7 | 129 | 390.00 |
| openai | gpt-4.1-nano | Active | 58m ago | 72.40 | 9 | 149 | 450.00 |
| together | mistral-7b | Active | 10d ago | 70.70 | 2 | 91 | 540.00 |
| openai | gpt-4o | Active | 57m ago | 69.90 | 13 | 173 | 1310.00 |
| deepinfra | mistral-7b | Stale(Medium) | 59m ago | 68.00 | 5 | 145 | 620.00 |
| fireworks | mixtral-8x22b | Active | 6d ago | 67.30 | 29 | 112 | 430.00 |
| gemini-2.5-flash | Never Succeeded(Medium) | 57m ago | 67.00 | 5 | 101 | 1030.00 | |
| deepinfra | devstral-small | Never Succeeded(Medium) | 59m ago | 62.50 | 9 | 140 | 580.00 |
| together | mixtral-8x7b | Active | 57m ago | 60.80 | 24 | 114 | 150.00 |
| deepinfra | mixtral-8x22b | Stale(Medium) | 17d ago | 59.40 | 14 | 78 | 400.00 |
| together | llama-3.2-3b | Active | 1d ago | 57.90 | 5 | 121 | 1480.00 |
| together | qwen-2.5-72b | Active | 29d ago | 55.70 | 49 | 63 | 340.00 |
| together | llama-3.3-70b | Active | 57m ago | 53.90 | 1 | 146 | 1350.00 |
| anthropic | claude-haiku-4.5 | Active | 1h ago | 51.80 | 19 | 74 | 550.00 |
| openai | gpt-4.1-mini | Active | 58m ago | 51.60 | 15 | 85 | 460.00 |
| fireworks | llama-3.3-70b | Active | 58m ago | 51.20 | 2 | 95 | 1390.00 |
| openai | o4 Mini | Never Succeeded(Medium) | 58m ago | 49.80 | 14 | 76 | 0.00 |
| deepinfra | llama-3.1-8b | Stale(Medium) | 59m ago | 48.20 | 4 | 96 | 560.00 |
| bedrock | llama-3.2-90b | Active | 8m ago | 47.10 | 6 | 51 | 350.00 |
| deepinfra | llama-3-8b | Stale(Medium) | 58m ago | 45.70 | 9 | 71 | 310.00 |
| together | deepseek-r1 | Active | 57m ago | 45.50 | 1 | 113 | 1000.00 |
| deepinfra | llama-3.2-1b | Stale(Medium) | 59m ago | 44.30 | 1 | 100 | 610.00 |
| deepinfra | llama-3.2-3b | Stale(Medium) | 59m ago | 43.50 | 2 | 98 | 530.00 |
| openai | gpt-4o-mini | Active | 57m ago | 42.90 | 20 | 95 | 360.00 |
| bedrock | mistral-large | Active | 8m ago | 42.00 | 3 | 47 | 380.00 |
| bedrock | claude-haiku-4.5 | Active | 8m ago | 41.90 | 4 | 62 | 1060.00 |
| gemini-2.5-pro | Never Succeeded(Medium) | 57m ago | 41.10 | 2 | 72 | 1690.00 | |
| openai | gpt-4.1 | Active | 58m ago | 38.60 | 6 | 82 | 500.00 |
| deepinfra | llama-3.2-90b | Stale(Medium) | 59m ago | 34.80 | 3 | 76 | 870.00 |
| deepinfra | llama-2-70b | Stale(Medium) | 58m ago | 34.80 | 3 | 57 | 570.00 |
| deepinfra | llama-3-70b | Stale(Medium) | 58m ago | 34.30 | 2 | 55 | 680.00 |
| bedrock | claude-3-7-sonnet | Active | 8m ago | 33.20 | 5 | 44 | 730.00 |
| deepinfra | qwen-2.5-72b | Stale(Medium) | 59m ago | 32.60 | 2 | 50 | 650.00 |
| openai | gpt-4-turbo | Active | 57m ago | 32.50 | 2 | 52 | 530.00 |
| bedrock | claude-3-5-sonnet | Active | 8m ago | 32.30 | 2 | 44 | 650.00 |
| deepinfra | Qwen 2.5 Coder 32B | Never Succeeded(Medium) | 1h ago | 31.50 | 1 | 75 | 2580.00 |
| bedrock | claude-3-5-haiku | Active | 8m ago | 30.90 | 4 | 38 | 680.00 |
| openai | GPT-5.1 | Active | 58m ago | 30.20 | 3 | 57 | 940.00 |
| openai | gpt-4 | Active | 57m ago | 27.90 | 3 | 47 | 660.00 |
| openai | GPT-5.2 | Active | 58m ago | 26.80 | 9 | 40 | 910.00 |
| openai | GPT-5.1-codex | Active | 58m ago | 25.90 | 3 | 48 | 1290.00 |
| openai | GPT-5.1-codex-mini | Active | 58m ago | 25.80 | 1 | 55 | 1160.00 |
| deepinfra | llama-3.1-405b | Stale(Medium) | 59m ago | 24.80 | 1 | 36 | 990.00 |
| together | llama-3.1-405b | Active | 29d ago | 24.50 | 24 | 25 | 450.00 |
| bedrock | claude-sonnet-4.5 | Active | 8m ago | 22.40 | 2 | 29 | 1610.00 |
| deepinfra | llama-3.1-70b | Stale(Medium) | 59m ago | 21.80 | 1 | 46 | 1110.00 |
| anthropic | claude-4-sonnet | Active | 1h ago | 20.30 | 1 | 31 | 1950.00 |
| anthropic | claude-opus-4.5 | Active | 1h ago | 20.10 | 2 | 33 | 1840.00 |
| bedrock | claude-3-opus | Active | 16d ago | 19.30 | 4 | 22 | 860.00 |
| deepinfra | llama-3.3-70b | Never Succeeded(Medium) | 59m ago | 18.90 | 1 | 46 | 2530.00 |
| bedrock | claude-opus-4.5 | Active | 8m ago | 18.50 | 4 | 24 | 1970.00 |
| anthropic | Claude Opus 4.1 | Active | 1h ago | 18.00 | 8 | 27 | 1480.00 |
| anthropic | claude-4-opus | Active | 1h ago | 17.70 | 5 | 24 | 1290.00 |
| deepinfra | llama-3.2-11b | Stale(Medium) | 59m ago | 13.30 | 1 | 62 | 2680.00 |
| openai | gpt-5.2-codex | Active | 58m ago | 12.90 | 1 | 27 | 1830.00 |
| deepinfra | qwen-3-235b | Never Succeeded(Medium) | 59m ago | 10.70 | 1 | 40 | 5860.00 |
| openai | o1-pro | Likely Deprecated(Medium) | 58m ago | 9.46 | 1 | 18 | 650.00 |
| openai | GPT-5.2-pro | Active | 58m ago | 8.59 | 4 | 14 | 4830.00 |
Lifecycle snapshot
Loading status summary…