LLM API pricing comparison

Sort and filter model input prices, output prices, context windows, and providers in one free LLM pricing comparison table.

How to use this tool

  1. Filter the table to a provider when you want a shorter list.
  2. Select a column heading to sort models by that metric.
  3. Compare input price, output price, and context window before choosing a model.

Worked example: Example: sort by output price to find models that may cost less for long generated reports.

MiMo-V2.5 (OpenRouter)OpenRouter$0.11$0.281M
DeepSeek V4 FlashDeepSeek$0.14$0.281M
GPT-5.4 nanoOpenAI$0.20$1.25400k
GLM-4.5 AirGLM$0.20$1.10128k
Gemini 3.1 Flash-LiteGoogle Gemini$0.25$1.501M
MiniMax M3Base rate through 512k input tokens; longer prompts use MiniMax's higher tier.MiniMax$0.30$1.201M
MiniMax M2.7MiniMax$0.30$1.20200k
MiniMax M2.5MiniMax$0.30$1.20200k
Qwen3.6 Plus (OpenRouter)OpenRouter$0.33$1.951M
DeepSeek V4 Pro (OpenRouter)OpenRouter$0.44$0.871M
DeepSeek V4 ProDeepSeek$0.44$0.871M
Qwen3.6 PlusInternational deployment base tier through 256k input tokens; longer prompts use Alibaba's $2 / $6 tier.Qwen$0.50$3.001M
GLM-4.6GLM$0.60$2.20200k
GPT-5.4 miniOpenAI$0.75$4.50400k
Kimi K2.7 CodeKimi$0.95$4.00262k
Kimi K2.6Kimi$0.95$4.00262k
GLM-5.1 (OpenRouter)OpenRouter$0.97$3.04203k
GPT-5.1OpenAI$1.25$10.00400k
GLM-5.1GLM$1.40$4.40203k
Kimi K2.7 Code HighspeedKimi$1.90$8.00262k
Gemini 3.1 Pro PreviewBase rate through 200k input tokens; longer prompts use Google's higher context tier.Google Gemini$2.00$12.001M
GPT-5.4OpenAI$2.50$15.001.05M
Claude Sonnet 4.6Anthropic$3.00$15.001M
GPT-5.5OpenAI$5.00$30.001.05M
Claude Opus 4.7Anthropic$5.00$25.001M
Claude Opus 4.6Anthropic$5.00$25.001M
GPT-5.5 ProOpenAI$30.00$180.001.05M

Bring your keys. Keep your savings.