Compare AI model pricing and benchmarks across providers including OpenAI, Anthropic, Google, AWS Bedrock, Azure, Mistral, and more. Filter by model capabilities like vision, function calling, and reasoning support. Find the most cost-effective model for your use case. Currently tracking 1,872 models across 102 providers.

The data is based on LiteLLM, maintained by the open-source community, and benchmark data from Artificial Analysis. The latest update occurred on March 25, 2026 at 12:00 AM UTC

Input/1M
to
Output/1M
to
Model
Provider
Input Price, $
Output Price, $
Price Compare
Context
Max Output
Intelligence
Coding
Openai O3Gradient AI2.008.00compare100KN/A38.4#3138.4#21
Anthropic Claude 3.7 SonnetGradient AI3.0015.00compare1KN/A30.8#4826.7#47
Openai O3 MiniGradient AI1.104.40compare100KN/A25.9#6717.9#85
Anthropic Claude 3.5 HaikuGradient AI0.8004.00compare1KN/A18.7#9710.7#130
Anthropic Claude 3 OpusGradient AI15.0075.00compare1KN/A18.0#16119.5#75
Openai GPT 4oGradient AIN/AN/Acompare16KN/A17.3#10816.7#88
DeepSeek R1 Distill Llama 70BGradient AI0.9900.990compare8KN/A16.0#11911.4#120
Anthropic Claude 3.5 SonnetGradient AI3.0015.00compare1KN/A15.9#12230.2#40
Llama3.3 70B InstructGradient AI0.6500.650compare2KN/A14.5#13610.7#130
Alibaba Qwen3 32BGradient AIN/AN/Acompare2KN/A14.5#136N/A
Openai GPT 4o MiniGradient AIN/AN/Acompare16KN/A12.6#160N/A
Llama3 8B InstructGradient AI0.2000.200compare512N/A6.4#2324.0#161
Mistral Nemo Instruct 2407Gradient AI0.3000.300compare512N/AN/AN/A