AI/REF
LLM Model Comparison
Compare context windows, pricing, modalities and strengths of leading LLMs side-by-side.
| Model | Vendor | Context | In /1M | Out /1M | Modality | Notes |
|---|---|---|---|---|---|---|
| GPT-4o | OpenAI | 128K | $2.50 | $10.00 | Text · Image · Audio | Fast multimodal flagship |
| GPT-4o mini | OpenAI | 128K | $0.15 | $0.60 | Text · Image | Cheap, strong for routine tasks |
| o1 | OpenAI | 200K | $15 | $60 | Text | Deep reasoning, slow |
| Claude 3.5 Sonnet | Anthropic | 200K | $3 | $15 | Text · Image | Great for coding & long context |
| Claude 3 Haiku | Anthropic | 200K | $0.25 | $1.25 | Text · Image | Fast, budget-friendly |
| Claude 3 Opus | Anthropic | 200K | $15 | $75 | Text · Image | Nuanced writing, expensive |
| Gemini 1.5 Pro | 2M | $1.25 | $5 | Text · Image · Audio · Video | Massive context window | |
| Gemini 1.5 Flash | 1M | $0.075 | $0.30 | Text · Image · Audio · Video | Ultra cheap, fast | |
| Llama 3.1 405B | Meta | 128K | $3 | $3 | Text | Open weights, GPT-4 class |
| Llama 3.1 70B | Meta | 128K | $0.59 | $0.79 | Text | Open, fast on Groq |
| Mistral Large 2 | Mistral | 128K | $2 | $6 | Text | Strong multilingual |
| DeepSeek V3 | DeepSeek | 64K | $0.27 | $1.10 | Text | Cheap frontier reasoning |
Reference only — providers change pricing and context limits regularly.
Related tools
All →AI/PROMPT
Prompt Library
Curated AI prompt templates plus a role-task-context prompt generator.
AI/TOKENS
AI Token Counter
Estimate GPT, Claude, Gemini, and Llama token counts and context window usage for any text.
AI/PRICING
AI Cost Calculator
Compare LLM API costs across GPT-4o, Claude, Gemini, Llama and more per call and at scale.
AI/PROMPT
AI Prompt Optimizer
Turn a rough idea into a structured role-task-context-format-constraints prompt for any LLM.