Skip to content
Sovyron

CloudFerro Sherlock

5 modelsProvider docs

As of Oct 4, 2026, CloudFerro Sherlock lists 5 supported models in the Sovyron catalog, including MiniMax-M2.5, GPT OSS 120B, Bielik 11B v2.6 Instruct, Bielik 11B v3.0 Instruct and Llama-3.3-70B-Instruct — minimax, gpt-oss and llama families. Its metered rates span $0.525–$2.92 per 1M tokens on a 3:1 input:output blend, and every price in the table is CloudFerro Sherlock's own, normalized to USD — 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 Oct 4, 2026
Model1M input1M output1M cache readContextReleased
MiniMax-M2.5$0.3$1.2—196kMar 5, 2026
GPT OSS 120B$2.92$2.92—131kAug 28, 2025
Bielik 11B v2.6 Instruct$0.67$0.67—32kMar 13, 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