Skip to content
Sovyron

Regolo AI

16 modelsProvider docs

As of Nov 22, 2026, Regolo AI lists 16 supported models in the Sovyron catalog, including Qwen3.8 27B, GLM-5.2, Gemma 4 31B IT, Mistral Small 4 119B and Qwen Image across the qwen, glm, gemma, mistral-small, qwen-image and model-router families. The cheapest rate in the table is Qwen3 Embedding 8B at $0.1 per 1M output tokens, the priciest GLM-5.2 at $6. On a 3:1 input:output blend the metered rates span $0.1–$3.2325 per 1M tokens, and every price is Regolo AI's own, normalized to USD. Offer mix: 3 free-tier offers. Open a model to compare it with the cheapest offer across all providers.

Supported models and pricing

16 of 16 models
Regolo AI model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleasedTags
Qwen3.8 27B$0.58$2.42—120kAug 14, 2026
GLM-5.2$2.31$6—96kJun 13, 2026
Gemma 4 31B IT$0.46$2.42—100kApr 2, 2026
Mistral Small 4 119B$0.5607$2.3552—256kMar 16, 2026
Qwen Image$0.5$2—8kMar 1, 2026
Qwen3.5 9B$0.0785$0.3925—262kFeb 23, 2026
Qwen3.5-122B$1.1215$4.7103—262kFeb 23, 2026
Brick Complexity Pro$0.12$0.46—100kFeb 6, 2026
Brick v1 Betafreefree—100kFeb 6, 2026free
Qwen3 Reranker 4B$0.12$0.12—33kFeb 1, 2026
DeepSeek OCR 2freefree—4kJan 27, 2026free
Apertus 70B$0.46$2.42—30kSep 2, 2025
GPT OSS 120B$1.1215$4.7103—128kAug 5, 2025
GPT OSS 20B$0.1121$0.471—128kAug 5, 2025
Qwen3 Embedding 8B$0.1$0.1—33kJun 5, 2025
Faster Whisper Large v3freefree—448Nov 6, 2023free