FREE TOOL · PRICES VERIFIED AUGUST 31, 2026

Compare LLM Models

Pick two or three models and see exactly how far apart they are — price per million tokens, context window, and what each one can actually do.

CHOOSE MODELS
VSVS
METRIC
MiniMax M3
MiniMax
GPT-5.6 Luna
OpenAI
Claude Haiku 4.5
Anthropic
Input $/1M$0.30+50%$0.20CHEAPEST$1.00+400%
Cached input $/1M$0.06+200%$0.02CHEAPEST$0.10+400%
Output $/1M$1.20CHEAPEST$1.20CHEAPEST$5.00+317%
Blended $/1M (3:1)$0.525+17%$0.45CHEAPEST$2.00+344%
Context window1.05M−0%1.05MLARGEST200K−81%
Capabilities
REASONINGVISIONVIDEO INPUTTOOL USEOPEN WEIGHTS
REASONINGVISIONTOOL USE
REASONINGVISIONTOOL USE

Percentages are relative to the best value in each row — cheapest price, largest context. Blended assumes a typical 3:1 input-to-output token ratio.

AFTER YOU PICK ONE

Whichever model wins, meter what your users burn through it.

ReqKey gives every API key a credit balance — validate, deduct, enforce limits, and see per-consumer spend in real time.

Start metering free