☁️ 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 | 318 tok/s |
| 2 | qwen-3-32b | groq | 225 tok/s |
| 3 | llama-4-scout | groq | 201 tok/s |
| 4 | llama-3.3-70b | groq | 201 tok/s |
| 5 | gpt-oss-120b | cerebras | 187 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 | 32m ago | 318.00 | 87 | 471 | 90.00 |
| cerebras | qwen-3-32b | Active | 23d ago | 267.00 | 32 | 444 | 240.00 |
| groq | qwen-3-32b | Active | 32m ago | 225.00 | 2 | 374 | 310.00 |
| groq | llama-4-scout | Active | 32m ago | 201.00 | 38 | 335 | 240.00 |
| groq | llama-3.3-70b | Active | 32m ago | 201.00 | 68 | 340 | 130.00 |
| groq | llama-4-maverick | Active | 2d ago | 199.00 | 1 | 307 | 620.00 |
| cerebras | llama-3.3-70b | Active | 23d ago | 189.00 | 17 | 316 | 410.00 |
| cerebras | gpt-oss-120b | Active | 6h ago | 187.00 | 1 | 380 | 1060.00 |
| cerebras | llama-3.1-8b | Active | 34m ago | 183.00 | 1 | 353 | 1190.00 |
| groq | kimi-k2 | Active | 32m ago | 141.00 | 12 | 215 | 310.00 |
| together | llama-3.1-8b | Active | 30m ago | 140.00 | 3 | 228 | 340.00 |
| bedrock | nova-micro | Active | 34m ago | 121.00 | 65 | 152 | 270.00 |
| openai | o3 Mini | Never Succeeded(Medium) | 31m ago | 109.00 | 8 | 160 | 0.00 |
| bedrock | llama-4-maverick | Active | 34m ago | 108.00 | 3 | 139 | 260.00 |
| bedrock | nova-lite | Active | 34m ago | 101.00 | 39 | 132 | 300.00 |
| bedrock | llama-4-scout | Active | 34m ago | 101.00 | 4 | 127 | 280.00 |
| bedrock | llama-3.3-70b | Active | 34m ago | 97.20 | 3 | 136 | 300.00 |
| together | qwen-2.5-7b | Active | 30m ago | 93.50 | 1 | 145 | 490.00 |
| bedrock | nova-pro | Active | 34m ago | 89.30 | 36 | 121 | 350.00 |
| openai | GPT-5.1-codex-max | Active | 31m ago | 80.20 | 11 | 118 | 1410.00 |
| openai | gpt-3.5-turbo | Active | 30m ago | 77.40 | 13 | 126 | 480.00 |
| deepinfra | mistral-7b | Stale(Medium) | 33m ago | 74.20 | 5 | 148 | 630.00 |
| gemini-2.5-flash-lite | Active | 30m ago | 73.70 | 10 | 132 | 550.00 | |
| together | llama-3.1-70b | Active | 14d ago | 72.50 | 12 | 129 | 360.00 |
| openai | gpt-4.1-nano | Active | 31m ago | 71.40 | 9 | 149 | 460.00 |
| together | mistral-7b | Active | 14d ago | 70.70 | 2 | 91 | 520.00 |
| openai | gpt-4o | Active | 30m ago | 69.60 | 13 | 173 | 1310.00 |
| deepinfra | devstral-small | Never Succeeded(Medium) | 34m ago | 68.40 | 9 | 140 | 600.00 |
| gemini-2.5-flash | Never Succeeded(Medium) | 30m ago | 67.30 | 5 | 101 | 1010.00 | |
| fireworks | mixtral-8x22b | Active | 32m ago | 67.00 | 29 | 111 | 430.00 |
| together | mixtral-8x7b | Active | 30m ago | 60.70 | 14 | 114 | 160.00 |
| deepinfra | mixtral-8x22b | Stale(Medium) | 21d ago | 59.20 | 14 | 77 | 470.00 |
| together | llama-3.2-3b | Active | 5d ago | 55.50 | 5 | 121 | 1600.00 |
| together | llama-3.3-70b | Active | 30m ago | 53.40 | 1 | 146 | 1270.00 |
| fireworks | llama-3.3-70b | Active | 32m ago | 53.10 | 1 | 95 | 1720.00 |
| anthropic | claude-haiku-4.5 | Active | 34m ago | 51.90 | 19 | 74 | 530.00 |
| openai | gpt-4.1-mini | Active | 31m ago | 51.40 | 15 | 109 | 460.00 |
| openai | o4 Mini | Never Succeeded(Medium) | 31m ago | 49.00 | 4 | 76 | 0.00 |
| together | deepseek-r1 | Active | 30m ago | 48.60 | 1 | 113 | 940.00 |
| bedrock | llama-3.2-90b | Active | 34m ago | 47.00 | 2 | 51 | 350.00 |
| deepinfra | llama-3-8b | Stale(Medium) | 32m ago | 45.80 | 20 | 71 | 310.00 |
| deepinfra | llama-3.1-8b | Stale(Medium) | 32m ago | 45.60 | 3 | 85 | 660.00 |
| deepinfra | llama-3.2-1b | Stale(Medium) | 32m ago | 44.30 | 1 | 100 | 740.00 |
| deepinfra | llama-3.2-3b | Stale(Medium) | 33m ago | 43.20 | 2 | 99 | 630.00 |
| bedrock | mistral-large | Active | 34m ago | 41.20 | 2 | 47 | 510.00 |
| gemini-2.5-pro | Never Succeeded(Medium) | 30m ago | 40.80 | 2 | 72 | 1690.00 | |
| bedrock | claude-haiku-4.5 | Active | 34m ago | 40.20 | 4 | 62 | 1150.00 |
| openai | gpt-4o-mini | Active | 30m ago | 39.90 | 18 | 65 | 370.00 |
| openai | gpt-4.1 | Active | 31m ago | 39.20 | 6 | 83 | 500.00 |
| deepinfra | llama-3.2-90b | Stale(Medium) | 33m ago | 35.10 | 3 | 82 | 810.00 |
| deepinfra | llama-2-70b | Stale(Medium) | 32m ago | 34.70 | 3 | 57 | 620.00 |
| deepinfra | llama-3-70b | Stale(Medium) | 32m ago | 33.80 | 2 | 55 | 720.00 |
| bedrock | claude-3-7-sonnet | Active | 34m ago | 32.90 | 2 | 44 | 740.00 |
| deepinfra | qwen-2.5-72b | Stale(Medium) | 33m ago | 32.50 | 1 | 50 | 810.00 |
| bedrock | claude-3-5-sonnet | Active | 34m ago | 32.40 | 2 | 44 | 660.00 |
| openai | gpt-4-turbo | Active | 30m ago | 32.40 | 2 | 52 | 530.00 |
| deepinfra | Qwen 2.5 Coder 32B | Never Succeeded(Medium) | 34m ago | 31.20 | 1 | 82 | 3020.00 |
| bedrock | claude-3-5-haiku | Active | 34m ago | 31.10 | 9 | 38 | 660.00 |
| openai | GPT-5.1 | Active | 31m ago | 29.50 | 3 | 57 | 1020.00 |
| openai | gpt-4 | Active | 30m ago | 27.60 | 3 | 47 | 670.00 |
| openai | GPT-5.2 | Active | 31m ago | 26.80 | 4 | 40 | 980.00 |
| deepinfra | llama-3.1-405b | Stale(Medium) | 32m ago | 26.10 | 3 | 39 | 720.00 |
| openai | GPT-5.1-codex | Active | 31m ago | 25.50 | 1 | 48 | 1290.00 |
| openai | GPT-5.4 | Active | 32m ago | 24.80 | 19 | 31 | 1540.00 |
| openai | GPT-5.1-codex-mini | Active | 31m ago | 24.60 | 1 | 55 | 1220.00 |
| deepinfra | llama-3.1-70b | Stale(Medium) | 32m ago | 22.20 | 1 | 46 | 1120.00 |
| bedrock | claude-sonnet-4.5 | Active | 34m ago | 22.10 | 2 | 29 | 1650.00 |
| anthropic | claude-opus-4.5 | Active | 34m ago | 20.30 | 2 | 33 | 1820.00 |
| anthropic | claude-4-sonnet | Active | 34m ago | 20.30 | 1 | 31 | 1960.00 |
| openai | GPT-5.3-codex | Active | 32m ago | 20.20 | 7 | 32 | 1250.00 |
| bedrock | claude-3-opus | Active | 20d ago | 19.50 | 8 | 22 | 850.00 |
| deepinfra | llama-3.3-70b | Never Succeeded(Medium) | 34m ago | 18.50 | 1 | 46 | 2520.00 |
| bedrock | claude-opus-4.5 | Active | 34m ago | 18.40 | 1 | 24 | 2050.00 |
| anthropic | Claude Opus 4.1 | Active | 34m ago | 17.80 | 8 | 27 | 1500.00 |
| anthropic | claude-4-opus | Active | 34m ago | 17.40 | 5 | 24 | 1310.00 |
| openai | gpt-5.2-codex | Active | 32m ago | 13.00 | 1 | 27 | 1800.00 |
| deepinfra | llama-3.2-11b | Stale(Medium) | 33m ago | 11.20 | 1 | 62 | 2690.00 |
| openai | o1-pro | Likely Deprecated(Medium) | 31m ago | 9.44 | 1 | 18 | 700.00 |
| openai | GPT-5.2-pro | Active | 31m ago | 8.57 | 4 | 14 | 4980.00 |
| deepinfra | qwen-3-235b | Never Succeeded(Medium) | 34m ago | 8.35 | 1 | 40 | 6890.00 |
Lifecycle snapshot
Loading status summary…