| Nemotron 3 Super 120B | aws | — | |
| GPT-5.4 | aws | — | - Input
- Input (cached read)
- Output
|
| GPT-5.5 | aws | — | - Input
- Input (cached read)
- Output
|
| gpt-oss-120b | aws | — | |
| gpt-oss-20b | aws | — | |
| Qwen3 32B (dense) | aws | — | |
| Qwen3-Coder-30B-A3B-Instruct | aws | — | |
| Qwen3-Coder-480B-A35B-Instruct | aws | — | |
| Qwen3-VL-235B-A22B-Instruct | aws | — | |
| Llama 3.3 70B | cerebras | 128,000 | - Input
$0.85 per 1M tokens medium- Output
$1.20 per 1M tokens medium
|
| Llama 3.1 8B | cerebras | 128,000 | - Input
$0.10 per 1M tokens medium- Output
$0.10 per 1M tokens medium
|
| Qwen 3 32B | cerebras | 128,000 | - Input
$0.40 per 1M tokens medium- Output
$0.80 per 1M tokens medium
|
| Command | cohere | 4,096 | - Input
$1.00 per 1M tokens medium- Output
$2.00 per 1M tokens medium
|
| Command R | cohere | 128,000 | |
| Command R+ | cohere | 128,000 | |
| Command R7B | cohere | — | |
| Qwen3 14B | qwen | — | |
| Qwen3 VL 30B A3B Instruct | qwen | — | |
| Qwen3.5 35B A3B | qwen | — | |
| Nemotron 3 Super 120B A12B | nvidia | 262,144 | - Input
- Input (cached read)
- Output
|
| Deepseek V3.2 | deepseek | 163,840 | - Input
$0.56 per 1M tokens medium- Input (cached read)
- Output
$1.68 per 1M tokens medium
|
| GLM-4.7 | z-ai | 202,800 | - Input
$0.60 per 1M tokens medium- Input (cached read)
- Output
$2.20 per 1M tokens medium
|
| GLM-5.1 | z-ai | 202,800 | - Input
$1.40 per 1M tokens medium- Input (cached read)
$0.26 per 1M tokens medium- Output
$4.40 per 1M tokens medium
|
| GLM 5.2 | z-ai | 1,048,576 | - Input
$1.40 per 1M tokens medium- Input (cached read, priority)
- Input (cached read)
$0.14 per 1M tokens medium- Input (priority)
…2 more prices |
| Kimi K2.5 | moonshotai | 262,144 | - Input
$0.60 per 1M tokens medium- Input (cached read)
$0.10 per 1M tokens medium- Output
$3.00 per 1M tokens medium
|