| Qwen3 Embedding 8B | qwen | 40,960 | |
| E5 Multi-Lingual Large Embeddings 0.6B | intfloat | 512 | |
| KB Whisper | kblab | 448 | - Input
- Output
- Output (audio)
|
| Qwen3.8 Max Preview | qwen | 1,000,000 | - Input
- Input (cache write)
- Input (cached read)
- Output
|
| GPT OSS 20B | groq | 131,072 | - Input
- Input (cached read)
- Output
|
| GPT OSS 120B | groq | 131,072 | - Input
- Input (cached read)
- Output
|
| SpaceXAI: Grok 4.3 | xai | 1,000,000 | - Input
- Input (>200k ctx)
$2.50 per 1M tokens medium- Input (batch, >200k ctx)
- Input (batch)
…9 more prices |
| Grok 4.20 (Reasoning) | xai | 1,000,000 | - Input
$1.25 per 1M tokens medium- Input (>200k ctx)
$2.50 per 1M tokens medium- Input (batch, >200k ctx)
- Input (batch)
…9 more prices |
| SpaceXAI: Grok 4.5 | xai | 500,000 | - Input
$2.00 per 1M tokens medium- Input (>200k ctx)
- Input (cached read, >200k ctx)
- Input (cached read)
$0.30 per 1M tokens unverified · disputed
…3 more prices |
| SpaceXAI: Grok Build 0.1 | xai | 256,000 | - Input
$1.00 per 1M tokens medium- Input (>200k ctx)
- Input (cached read, >200k ctx)
- Input (cached read)
$0.20 per 1M tokens medium
…3 more prices |
| Grok 4.20 (Non-Reasoning) | xai | 1,000,000 | - Input
$1.25 per 1M tokens medium- Input (>200k ctx)
$2.50 per 1M tokens medium- Input (batch, >200k ctx)
- Input (batch)
…9 more prices |
| GPT OSS 120B | cerebras | 131,072 | - Input
$0.35 per 1M tokens medium- Input (cached read)
- Output
$0.75 per 1M tokens medium
|
| Kimi K2.6 (Baidu) | baidu | 262,144 | - Input
- Input (cached read)
- Output
|
| GLM-5.2 (Baidu) | baidu | 1,048,576 | - Input
- Input (cached read)
- Output
|
| DeepSeek V4 Flash (Baidu) | baidu | 1,048,576 | - Input
- Input (cached read)
- Output
|
| GLM-5 (Baidu) | baidu | 202,752 | - Input
- Input (cached read)
- Output
|
| GLM-5.1 (Baidu) | baidu | 202,752 | - Input
- Input (cached read)
- Output
|
| DeepSeek V4 Pro (Baidu) | baidu | 1,048,576 | - Input
- Input (cached read)
- Output
|
| GLM-5.3 (Baidu) | baidu | 1,048,576 | - Input
- Input (cached read)
- Output
|
| GPT-5.6 Sol (AWS Mantle) | aws-mantle | 921,600 | - Input
- Input (cache write)
- Input (cached read)
- Output
|
| GPT-6 Astra (AWS Mantle) | aws-mantle | 1,050,000 | - Input
- Input (cache write)
- Input (cached read)
- Output
|
| GPT-5.6 Luna (AWS Mantle) | aws-mantle | 921,600 | - Input
- Input (cache write)
- Input (cached read)
- Output
|
| GPT-5.6 Terra (AWS Mantle) | aws-mantle | 921,600 | - Input
- Input (cache write)
- Input (cached read)
- Output
|
| MiniMax M2.7 (Gonka24) | gonka24 | 204,800 | - Input
- Input (cached read)
- Output
|
| DeepSeek V4 Flash (Gonka24) | gonka24 | 390,000 | - Input
- Input (cached read)
- Output
|