LLM API prices, side by side Updated 11 Sept 2026
Compare LLM API prices per token for GPT, Claude, Gemini, DeepSeek, Qwen, Llama, Mistral and Grok across OpenRouter, OpenCode Zen, OrcaRouter, Requesty, Nano-GPT and the first-party labs. Every rate is normalised to USD per 1M tokens.
Search models Sort by Released 1M output 1M input 1M cache read Blended (3:1) Providers Context ↓ Open weights Reasoning ≥3 providers133 of 133 models
Browse all 602 comparable models Open the comparison matrix
Data:models.dev · Cheapest input, output and cached input price per model, in USD per 1M tokens; free tiers and subscriptions excluded· updated 11 Sept 2026
llmprice compares LLM API prices for 1,898 models across 213 providers: the cheapest input, output and cached input price per model, normalized to USD per 1M tokens, across OpenRouter, OpenCode Zen, OrcaRouter, Requesty, Nano-GPT and the first-party APIs from OpenAI, Anthropic, Google, DeepSeek and xAI. Sort by price, context window or release date, filter by open weights, reasoning or provider count, or open the comparison matrix to see every provider side by side. Free and subscription-plan offers are flagged, and the same numbers are published as catalog.json and llms.txt — no signup, no API key.
llms.txt catalog.json sitemap
Language: 🌐 English 🇬🇧 English (UK) 🇦🇺 English (Australia) 🇨🇦 English (Canada) 🇮🇳 हिन्दी 🇨🇳 中文 🇯🇵 日本語 🇰🇷 한국어 🇮🇩 Bahasa Indonesia 🇻🇳 Tiếng Việt 🇵🇭 Filipino 🇧🇷 Português (Brasil) 🇪🇸 Español 🇲🇽 Español (México) 🇩🇪 Deutsch 🇫🇷 Français 🇮🇹 Italiano 🇵🇱 Polski 🇷🇺 Русский 🇹🇷 Türkçe