Privatemode AI
Inference provider
- Endpoints
- 8
- Models
- 8
Models served
8 shown
| Model | Creator | Type | In $/1M | Out $/1M | Context | Max output | Tools | Region |
|---|---|---|---|---|---|---|---|---|
| DeepSeek OCR 2 deepseek-ocr-2 | DeepSeek | Chat | $0.89 | $1.47 | 8.2K | 8.2K | Region not stated | |
| GLM-5.3 glm-5.3 | Z.ai (Zhipu AI) | Chat | $1.79 | $6.63 | 1M | 131K | Region not stated | |
| GLM-5.3-Flash glm-5.3-flash | Z.ai (Zhipu AI) | Chat | $0.231 | $0.751 | 1M | 131K | Region not stated | |
| GPT-OSS 120B gpt-oss-120b | OpenAI | Chat | $0.231 | $0.751 | 128K | 32.8K | Region not stated | |
| Kimi K2.6 kimi-k2.6 | Moonshot AI | Chat | $1.79 | $8.94 | 256K | 262K | Region not stated | |
| Qwen 3 Embedding 4B qwen3-embedding-4b | Alibaba (Qwen) | Embedding | $0.15 | $0 | 32K | 2.6K | Region not stated | |
| Voxtral Mini 3B voxtral-mini-3b | Mistral AI | Chat | $0.00462 | $0 | 32K | 32K | Region not stated | |
| Whisper Large v3 whisper-large-v3 | OpenAI | Transcription | $0.0162 | $0 | 448 | 4.1K | Region not stated |
One row per model and variant. Dated pins appear on the model page, not as separate rows. Prices are indicative; verify with the provider.