Large Language Models
docAnalyzer.ai is committed to staying at the forefront of AI technology, offering the latest models from leading providers including Anthropic, DeepSeek, Google, Meta, OpenAI and xAI. Our rapid deployment infrastructure enables us to make new models available within days—sometimes hours—of their release, ensuring you always have access to cutting-edge AI capabilities. Unlike most competitors who limit you to a single provider, we provide an extensive selection of models, giving you the freedom to choose the perfect AI for your specific needs. Each model is meticulously evaluated for quality and speed, providing you with the necessary power to chat with your documents and create AI agents. Below are the detailed specifications of each available model.
Model | Quality | Speed | Latency* |
---|---|---|---|
GPT-5 OpenAI | 69 | 109.4 token/s | 74.53 seconds |
Grok 4 xAI | 68 | 51 token/s | 6.43 seconds |
Gemini 2.5 Pro Google Gemini | 65 | 143.5 token/s | 30.39 seconds |
GPT-5 mini OpenAI | 64 | 74.9 token/s | 28.68 seconds |
openai/gpt-oss-120b Groq | 61 | 226.1 token/s | 0.44 seconds |
Claude Opus 4.1 Anthropic | 61 | 24.7 token/s | 1.48 seconds |
Claude Sonnet 4 Anthropic | 59 | 48.1 token/s | 1.38 seconds |
DeepSeek R1 DeepSeek | 59 | 20.1 token/s | 2.82 seconds |
Gemini 2.5 Flash Google Gemini | 58 | 257.4 token/s | 14.08 seconds |
Grok 3 mini xAI | 58 | 187.9 token/s | 0.62 seconds |
GPT-5 nano OpenAI | 54 | 190.7 token/s | 33.68 seconds |
openai/gpt-oss-20b Groq | 49 | 262.7 token/s | 0.43 seconds |
moonshotai/kimi-k2-instruct Groq | 49 | 53.2 token/s | 0.56 seconds |
DeepSeek V3 DeepSeek | 49 | 19.9 token/s | 2.93 seconds |
Gemini 2.5 Flash-Lite Google Gemini | 47 | 423 token/s | 8.81 seconds |
GPT 4.1 OpenAI | 47 | 128.5 token/s | 0.53 seconds |
GPT 4.1 mini OpenAI | 46 | 57.6 token/s | 0.47 seconds |
meta-llama/llama-4-maverick-17b-128e-instruct Groq | 42 | 146.6 token/s | 0.32 seconds |
meta-llama/llama-4-scout-17b-16e-instruct Groq | 33 | 114.7 token/s | 0.39 seconds |
GPT 4.1 nano OpenAI | 32 | 173 token/s | 0.37 seconds |
Gemini 2.0 Flash-Lite Google Gemini | 30 | 173.8 token/s | 0.25 seconds |
Claude 3.5 Haiku Anthropic | 23 | 54.1 token/s | 0.57 seconds |
* Latency progress bars use a logarithmic scale, where lower latency values indicate better performance.