Fastest AI Models
23 LLMs ranked by speed (tokens per second). For latency-sensitive applications like chatbots, real-time coding, and interactive agents.
Note: Speed ratings are relative estimates. For production latency data, we recommend Artificial Analysis. See also: Full Speed Comparison with TTFT and provider endpoint data.
8
Ultra Fast (100+ tok/s)
12
Fast (50–99 tok/s)
2
Moderate (20–49 tok/s)
1
Slower (<20 tok/s)
Speed Ranking
Full Table
| # | Model | Speed | Price |
|---|---|---|---|
| 1 | Gemini 2.5 Flash (batch) Google | 350 tok/s | $0.15 |
| 2 | GPT-4.1 Nano (batch) OpenAI | 200 tok/s | $0.05 |
| 3 | GPT-4.1 Mini (batch) OpenAI | 160 tok/s | $0.20 |
| 4 | Mistral Small 3.1 24B OSS Mistral | 150 tok/s | $0.35 |
| 5 | GPT-4o-mini (batch) OpenAI | 150 tok/s | $0.07 |
| 6 | Llama 4 Scout OSS Meta | 120 tok/s | $0.18 |
| 7 | GPT-4.1 (batch) OpenAI | 110 tok/s | $1.00 |
| 8 | GPT-4o (batch) OpenAI | 100 tok/s | $1.25 |
| 9 | Llama 4 Maverick OSS Meta | 95 tok/s | $0.19 |
| 10 | Claude Sonnet 4.6 (batch) Anthropic | 90 tok/s | $3.00 |
| 11 | Gemini 2.5 Pro Google | 90 tok/s | $1.25 |
| 12 | GPT-5.2 OpenAI | 85 tok/s | $0.88 |
| 13 | Claude Sonnet 4 Anthropic | 80 tok/s | $3.00 |
| 14 | Mistral Large OSS Mistral | 80 tok/s | $2.00 |
| 15 | Llama 3.3 70B Instruct OSS Meta | 80 tok/s | $0.59 |
| 16 | GPT-5 (batch) OpenAI | 75 tok/s | $0.63 |
| 17 | O4 Mini OpenAI | 65 tok/s | $0.55 |
| 18 | Qwen2.5 72B Instruct OSS Alibaba | 65 tok/s | $0.36 |
| 19 | o3 Mini (batch) OpenAI | 60 tok/s | $0.55 |
| 20 | Claude Opus 4.6 (batch) Anthropic | 50 tok/s | $5.00 |
| 21 | DeepSeek V3.2 OSS DeepSeek | 49 tok/s | $0.29 |
| 22 | DeepSeek R1 OSS DeepSeek | 30 tok/s | $0.70 |
| 23 | O3 OpenAI | 15 tok/s | $1.00 |