Privatemode AI
9 modelsProvider docs
As of Nov 22, 2026, Privatemode AI lists 9 supported models in the Sovyron catalog, including GLM Flash Latest, GLM-5.3-Flash, GLM Latest, GLM-5.3 and DeepSeek OCR 2 across the glm-flash, glm, deepseek-ocr, gpt-oss, voxtral-mini and qwen-embedding families. The cheapest rate in the table is GLM Flash Latest at $0.7511 per 1M output tokens, the priciest GLM-5.3 at $6.6326. On a 3:1 input:output blend the metered rates span $0.0035–$3.0014 per 1M tokens, and every price is Privatemode AI's own, normalized to USD. Offer mix: metered per-token rates only, with no free-tier or subscription offers in the catalog. Open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
9 of 9 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| GLM Flash Latest | $0.2311 | $0.7511 | $0.0578 | 1.0M | Aug 26, 2026 |
| GLM-5.3-Flash | $0.2311 | $0.7511 | $0.0578 | 1.0M | Aug 26, 2026 |
| GLM Latest | $1.791 | $6.6326 | $0.1733 | 1.0M | Aug 14, 2026 |
| GLM-5.3 | $1.791 | $6.6326 | $0.1733 | 1.0M | Aug 14, 2026 |
| DeepSeek OCR 2 | $0.8897 | $1.4675 | $0.0924 | 8k | Jan 27, 2026 |
| GPT OSS 120B | $0.2311 | $0.7511 | $0.0462 | 128k | Aug 5, 2025 |
| Voxtral Mini 3B | $0.0046 | free | — | 32k | Jul 15, 2025 |
| Qwen3 Embedding 4B | $0.1502 | free | — | 32k | Jun 5, 2025 |
| Whisper Large v3 | $0.0162 | free | — | 448 | Nov 6, 2023 |