Skip to content
Sovyron

CloudFerro Sherlock

5 modelsProvider docs

As of Nov 22, 2026, CloudFerro Sherlock lists 5 supported models in the Sovyron catalog, including GLM-5.3, MiniMax-M2.5, GPT OSS 120B, Bielik 11B v3.0 Instruct and Llama-3.3-70B-Instruct across the glm, minimax-m, gpt-oss and llama families. The cheapest rate in the table is Bielik 11B v3.0 Instruct at $0.67 per 1M output tokens, the priciest GLM-5.3 at $4.48. On a 3:1 input:output blend the metered rates span $0.525–$2.92 per 1M tokens, and every price is CloudFerro Sherlock'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

5 of 5 models
CloudFerro Sherlock model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleased
GLM-5.3$0.34$4.48—262kAug 14, 2026
MiniMax-M2.5$0.3$1.2—196kFeb 12, 2026
GPT OSS 120B$2.92$2.92—131kAug 5, 2025
Bielik 11B v3.0 Instruct$0.67$0.67—32kMar 13, 2025
Llama-3.3-70B-Instruct$2.92$2.92—70kDec 6, 2024