Speed & Latency
Output speed (tokens per second) and latency (time to first token) benchmarks across models and providers.
Filters:
Provider:
Creators:
Speed vs Intelligence
EUGlobal
Drag to zoom ยท Click to pin55 models
| # | Model | Creator | Output Speed (t/s)โ | Latency TTFT (s) | Total Response (s) | Intelligence | Price $/1M |
|---|---|---|---|---|---|---|---|
| 1 | Gemini 2.5 Flash-LiteEU | 250.4 t/s | 19.12s | - | 17.6 | $0.17 | |
| 2 | Gemini 2.5 FlashREU | 193.7 t/s | 12.75s | - | 27 | $0.85 | |
| 3 | GPT-4.1 NanoEU | OpenAI | 181 t/s | 0.48s | - | 13 | $0.17 |
| 4 | Nova 2 LiteREU | Amazon | 174.7 t/s | 13.30s | - | 34.5 | $0.85 |
| 5 | Gemini 3 FlashRGlobal | 170 t/s | 5.43s | - | 46.4 | $1.13 | |
| 6 | GPT-5.4 NanoRGlobal | OpenAI | 162.2 t/s | 2.66s | - | 44 | $0.46 |
| 7 | GPT-5.4 MiniRGlobal | OpenAI | 161 t/s | 4.37s | - | 48.9 | $1.69 |
| 8 | GPT-5 NanoREU | OpenAI | 159.6 t/s | 62.37s | - | 26.8 | $0.14 |
| 9 | Mistral Small 4ROpenGlobal | Mistral | 155.2 t/s | 0.53s | - | 27.8 | $0.26 |
| 10 | Nemotron 3 SuperROpenGlobal | NVIDIA | 152.5 t/s | 0.77s | - | 36 | $0.41 |
| 11 | o3-miniREU | OpenAI | 148.6 t/s | 19.20s | - | 25.2 | $1.93 |
| 12 | Grok 4.20RGlobal | xAI | 140 t/s | 12.56s | - | 49.3 | $3.00 |
| 13 | GPT-4oEU | OpenAI | 136 t/s | 0.49s | - | 17.3 | $4.38 |
| 14 | o4-miniREU | OpenAI | 130.1 t/s | 13.44s | - | 33.1 | $1.93 |
| 15 | Gemini 3 ProRGlobal | 125.8 t/s | 27.92s | - | 48.4 | $4.50 | |
| 16 | Gemini 3.1 ProRGlobal | 123.3 t/s | 19.86s | - | 57.2 | $4.50 | |
| 17 | Grok 4.1 FastRGlobal | xAI | 116.5 t/s | 9.48s | - | 38.6 | $0.28 |
| 18 | Llama 4 MaverickOpenGlobal | Meta | 113 t/s | 0.61s | - | 18.4 | $0.47 |
| 19 | Gemini 2.5 ProREU | 110.3 t/s | 25.80s | - | 34.6 | $3.44 | |
| 20 | o1REU | OpenAI | 108.5 t/s | 19.13s | - | 30.8 | $26.25 |
| 21 | Claude Haiku 4.5REU | Anthropic | 106.6 t/s | 9.60s | - | 37.1 | $2.00 |
| 22 | GPT-5.1REU | OpenAI | 105.6 t/s | 13.78s | - | 47.7 | $3.44 |
| 23 | Llama 3.3 70BOpenGlobal | Meta | 96.1 t/s | 0.55s | - | 14.5 | $0.61 |
| 24 | GPT-4.1EU | OpenAI | 86.3 t/s | 0.70s | - | 26.3 | $3.50 |
| 25 | GPT-4.1 MiniEU | OpenAI | 85 t/s | 0.59s | - | 22.9 | $0.70 |
| 26 | GPT-5REU | OpenAI | 81.3 t/s | 64.94s | - | 44.6 | $3.44 |
| 27 | o3REU | OpenAI | 79.8 t/s | 6.27s | - | 38.4 | $3.50 |
| 28 | GPT-5.4RGlobal | OpenAI | 76.5 t/s | 169.45s | - | 56.8 | $5.63 |
| 29 | GPT-5 MiniREU | OpenAI | 76.3 t/s | 69.23s | - | 41.2 | $0.69 |
| 30 | GLM-5RGlobal | Z AI | 71 t/s | 0.77s | - | 49.8 | $1.55 |
| 31 | GPT-5.3 CodexRGlobal | OpenAI | 65.1 t/s | 53.13s | - | 53.6 | $4.81 |
| 32 | GPT-5.2RGlobal | OpenAI | 60.8 t/s | 48.31s | - | 51.3 | $4.81 |
| 33 | MiMo V2 ProROpenGlobal | Xiaomi | 58.2 t/s | 2.59s | - | 49.2 | $1.50 |
| 34 | GPT-4o MiniEU | OpenAI | 58.1 t/s | 0.55s | - | 12.6 | $0.26 |
| 35 | MiniMax M2.5RGlobal | MiniMax | 57 t/s | 2.46s | - | 41.9 | $0.53 |
| 36 | Grok 4RGlobal | xAI | 54.2 t/s | 6.77s | - | 41.5 | $6.00 |
| 37 | Mistral Large 3OpenGlobal | Mistral | 53.9 t/s | 0.63s | - | 22.8 | $0.75 |
| 38 | Qwen3.6 PlusRGlobal | Alibaba | 52.1 t/s | 1.54s | - | 50 | $1.13 |
| 39 | Qwen3.5 397BROpenGlobal | Alibaba | 52 t/s | 1.52s | - | 45 | $1.35 |
| 40 | Claude Sonnet 4.6REU | Anthropic | 51.2 t/s | 32.92s | - | 51.7 | $6.00 |
| 41 | Claude Opus 4.5REU | Anthropic | 50.9 t/s | 12.65s | - | 49.7 | $10.00 |
| 42 | GLM-5.1RGlobal | Z AI | 45 t/s | 0.93s | - | 51.4 | $2.15 |
| 43 | Claude Opus 4.6REU | Anthropic | 42.3 t/s | 10.52s | - | 53 | $10.00 |
| 44 | Claude Sonnet 4REU | Anthropic | 41.3 t/s | 8.79s | - | 38.7 | $6.00 |
| 45 | Claude Sonnet 4.5REU | Anthropic | 39.3 t/s | 8.51s | - | 43 | $6.00 |
| 46 | MiniMax M2.7RGlobal | MiniMax | 37.7 t/s | 2.31s | - | 49.6 | $0.53 |
| 47 | Kimi K2.5RGlobal | Kimi | 32.4 t/s | 3.99s | - | 46.8 | $1.20 |
| 48 | DeepSeek V3.2 (Non-reasoning)OpenGlobal | DeepSeek | 31.9 t/s | 1.43s | - | 32.1 | $0.32 |
| 49 | DeepSeek V3.2ROpenGlobal | DeepSeek | 31.4 t/s | 1.38s | - | 41.7 | $0.32 |
| 50 | Claude 3.7 SonnetREU | Anthropic | - | - | - | 34.7 | $6.00 |
| 51 | Muse SparkRGlobal | Meta | - | - | - | 52.1 | $0.00 |
| 52 | SonarGlobal | Perplexity | - | - | - | - | $1.00 |
| 53 | Sonar ProGlobal | Perplexity | - | - | - | - | $12.00 |
| 54 | Sonar Reasoning ProRGlobal | Perplexity | - | - | - | - | $6.50 |
| 55 | Sonar Deep ResearchRGlobal | Perplexity | - | - | - | - | $6.50 |