| GLM 5.2 Short Flex | neuralwatt | 199.984 | - Input
0,9425 $ pro 1M tokens niedrig- Input (cached read)
0,0943 $ pro 1M tokens niedrig- Output
2,93 $ pro 1M tokens niedrig
|
| GLM 5.2 Flex | neuralwatt | 1.048.560 | - Input
0,9425 $ pro 1M tokens niedrig- Input (cached read)
0,0943 $ pro 1M tokens niedrig- Output
2,93 $ pro 1M tokens niedrig
|
| Kimi K2.7 Code Flex | neuralwatt | 262.128 | - Input
0,6175 $ pro 1M tokens niedrig- Input (cached read)
0,0618 $ pro 1M tokens niedrig- Output
2,60 $ pro 1M tokens niedrig
|
| Kimi K2.7 Code Fast | neuralwatt | 262.128 | - Input
0,95 $ pro 1M tokens niedrig- Input (cached read)
0,095 $ pro 1M tokens niedrig- Output
4,00 $ pro 1M tokens niedrig
|
| GLM 5.2 Short Fast | neuralwatt | 199.984 | - Input
1,45 $ pro 1M tokens niedrig- Input (cached read)
0,145 $ pro 1M tokens niedrig- Output
4,50 $ pro 1M tokens niedrig
|
| Kimi K3 | neuralwatt | 1.040.384 | - Input
3,00 $ pro 1M tokens niedrig- Input (cached read)
0,30 $ pro 1M tokens niedrig- Output
15,00 $ pro 1M tokens niedrig
|
| GLM-5.2 | neuralwatt | 1.000.000 | - Input
1,45 $ pro 1M tokens niedrig- Input (cached read)
0,145 $ pro 1M tokens niedrig- Output
4,50 $ pro 1M tokens niedrig
|
| Kimi K3 Flex | neuralwatt | 1.048.560 | - Input
1,95 $ pro 1M tokens niedrig- Input (cached read)
0,195 $ pro 1M tokens niedrig- Output
9,75 $ pro 1M tokens niedrig
|
| Qwen3.6 35B Fast | neuralwatt | 131.056 | - Input
0,29 $ pro 1M tokens niedrig- Input (cached read)
0,029 $ pro 1M tokens niedrig- Output
1,15 $ pro 1M tokens niedrig
|
| Gemma 4 31B | neuralwatt | 262.128 | - Input
0,144 $ pro 1M tokens niedrig- Input (cached read)
0,0144 $ pro 1M tokens niedrig- Output
0,42 $ pro 1M tokens niedrig
|
| DeepSeek V4 Flash Flex | neuralwatt | 1.048.560 | - Input
0,091 $ pro 1M tokens niedrig- Input (cached read)
0,0182 $ pro 1M tokens niedrig- Output
0,182 $ pro 1M tokens niedrig
|
| Qwen3.6 35B-A3B | neuralwatt | 256.000 | - Input
0,29 $ pro 1M tokens niedrig- Input (cached read)
0,029 $ pro 1M tokens niedrig- Output
1,15 $ pro 1M tokens niedrig
|
| Qwen3.8 27B | neuralwatt | 262.128 | - Input
0,99 $ pro 1M tokens niedrig- Input (cached read)
0,99 $ pro 1M tokens niedrig- Output
1,49 $ pro 1M tokens niedrig
|
| GLM 5.2 Short | neuralwatt | 199.984 | - Input
1,45 $ pro 1M tokens niedrig- Input (cached read)
0,145 $ pro 1M tokens niedrig- Output
4,50 $ pro 1M tokens niedrig
|
| Qwen3 Coder 30B A3B Instruct | qwen | 262.144 | - Input
0,1146 $ pro 1M tokens niedrig- Output
0,7481 $ pro 1M tokens niedrig
|
| Qwen3 30B A3B Instruct 2507 | qwen | 262.144 | - Input
0,30 $ pro 1M tokens niedrig- Output
0,50 $ pro 1M tokens niedrig
|
| Qwen3 30B A3B Thinking 2507 | qwen | 262.144 | - Input
0,36 $ pro 1M tokens niedrig- Output
1,30 $ pro 1M tokens niedrig
|
| MM Poly 8B | clarifai | 32.768 | - Input
0,658 $ pro 1M tokens niedrig- Output
1,11 $ pro 1M tokens niedrig
|
| DeepSeek OCR | deepseek | 8.192 | - Input
0,20 $ pro 1M tokens niedrig- Output
0,70 $ pro 1M tokens niedrig
|
| Ministral 3 14B Reasoning 2512 | mistral | 262.144 | - Input
2,50 $ pro 1M tokens niedrig- Output
1,70 $ pro 1M tokens niedrig
|
| Ministral 3 3B Reasoning 2512 | mistral | 262.144 | - Input
1,04 $ pro 1M tokens niedrig- Output
0,5483 $ pro 1M tokens niedrig
|
| MiniMax-M2.5 High Throughput | minimax | 204.800 | - Input
0,30 $ pro 1M tokens niedrig- Output
1,20 $ pro 1M tokens niedrig
|
| Kimi K2.6 | moonshotai | 262.144 | - Input
0,95 $ pro 1M tokens niedrig- Output
4,00 $ pro 1M tokens niedrig
|
| Trinity Mini | arcee-ai | 131.072 | - Input
0,045 $ pro 1M tokens niedrig- Output
0,15 $ pro 1M tokens niedrig
|
| Morph: Morph V3 Large | morph | 262.144 | - Input
0,90 $ pro 1M tokens mittel- Output
1,90 $ pro 1M tokens mittel
|