AI Model Comparison
Compare AI model pricing and benchmarks across providers including OpenAI, Anthropic, Google, Amazon 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 2,597 models across 98 providers. Last update:
Model | Creator | Input Price, $ | Output Price, $ | Inference Providers | Context | Max Output | Intelligence | Coding | |
|---|---|---|---|---|---|---|---|---|---|
| Kimi K2.5 | 0.440 | 2.00 | compare (11) | 262K | 98K | 46.8#1 | 39.5#1 | ||
| MiniMax M2.5 | 0.150 | 1.15 | compare (7) | 1.0M | 131K | 41.9#2 | 37.4#2 | ||
| GPT OSS 120B | 0.039 | 0.180 | compare (20) | 131K | 131K | 33.3#3 | 28.6#3 | ||
| DeepSeek V3.1 | 0.135 | 0.500 | compare (14) | 164K | 66K | 28.1#4 | 28.4#4 | ||
| GLM-4.5 | 0.400 | 1.60 | compare (8) | 131K | 98K | 26.4#5 | 26.3#5 | ||
| Qwen3 Coder 480B A35B Instruct | 0.220 | 1.30 | compare (8) | 262K | 66K | 24.8#6 | 24.6#6 | ||
| GPT OSS 20B | 0.030 | 0.140 | compare (16) | 131K | 131K | 24.5#7 | 18.5#8 | ||
| DeepSeek V3 324 | 0.200 | 0.400 | compare (12) | 164K | 16K | 22.3#8 | 22.0#7 | ||
| Qwen3 235B A22B Instruct | 0.090 | 0.580 | compare (9) | 262K | 33K | 17.0#9 | 14.0#9 | ||
| Llama 3.3 70B Instruct | 0.100 | 0.200 | compare (19) | 131K | 120K | 14.5#10 | 10.7#10 | ||
| Llama 3.1 8B Instruct | 0.020 | 0.030 | compare (19) | 200K | 128K | 11.8#11 | 4.9#11 | ||
| DeepSeek R1 528 | 0.200 | 0.250 | compare (11) | 164K | 33K | N/A | N/A | ||
| Kimi K2 Instruct | 0.500 | 2.00 | compare (9) | 262K | 33K | N/A | N/A | ||
| Llama 4 17B Scout Instruct | 0.050 | 0.100 | compare (11) | 10.0M | 16K | N/A | N/A | ||
| Phi-4 Mini Instruct | 0.075 | 0.300 | compare (2) | 131K | 4K | N/A | N/A | ||
| Qwen3 235B A22B Thinking | 0.149 | 0.880 | compare (9) | 262K | 33K | N/A | N/A |