Obscurify.ai
15 modelsProvider docs
As of Nov 22, 2026, Obscurify.ai lists 15 supported models in the Sovyron catalog, including MiniMax-M3.1-Flash, Claude Haiku 5.5, Claude Sonnet 5.5, GPT-6 Luna and Grok 4.7 across the minimax-m-flash, claude-haiku, claude-sonnet, gpt-luna, grok and gemini-flash families. The cheapest rate in the table is GLM-5.3-Flash at $0.1019 per 1M output tokens, the priciest GPT-5.5 at $33.15. On a 3:1 input:output blend the metered rates span $0.0644–$12.4313 per 1M tokens, and every price is Obscurify.ai's own, normalized to USD. Offer mix: 1 free-tier offer. Open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
15 of 15 models
| Model | 1M input | 1M output | 1M cache read | Context | Released | Tags |
|---|---|---|---|---|---|---|
| MiniMax-M3.1-Flash | $0.1658 | $0.663 | $0.0166 | 1.0M | Oct 19, 2026 | |
| Claude Haiku 5.5 | $0.1105 | $0.5525 | $0.0111 | 1.0M | Oct 7, 2026 | |
| Claude Sonnet 5.5 | $2.21 | $11.05 | $0.1105 | 1.0M | Sep 28, 2026 | |
| GPT-6 Luna | $0.1105 | $0.5525 | $0.0111 | 1.1M | Sep 22, 2026 | |
| Grok 4.7 | $2.21 | $6.63 | $0.5525 | 500k | Sep 21, 2026 | |
| Gemini 3.8 Flash | $0.8287 | $4.1437 | $0.0829 | 1.0M | Sep 2, 2026 | |
| GLM-5.3-Flash | $0.0519 | $0.1019 | — | 1.0M | Aug 26, 2026 | |
| GLM-5.3 | $0.663 | $1.2155 | $0.221 | 1.0M | Aug 14, 2026 | |
| Qwen3.8 27B | $0.1658 | $0.7735 | $0.0442 | 262k | Aug 14, 2026 | |
| DeepSeek V4 Pro 0813 | $0.7293 | $2.7625 | $0.0442 | 1.0M | Aug 13, 2026 | |
| DeepSeek V4 Flash | free | free | — | 1.0M | Apr 24, 2026 | free |
| GPT-5.5 | $5.525 | $33.15 | $0.5525 | 1.1M | Apr 23, 2026 | |
| Kimi K2 Instruct 0905 | $0.78 | $3.25 | — | 262k | Sep 5, 2025 | |
| Qwen3-Coder 480B-A35B Instruct | $0.3315 | $1.105 | — | 262k | Jul 22, 2025 | |
| Llama-3.3-70B-Instruct | $0.0553 | $0.2541 | — | 128k | Dec 6, 2024 |