Skip to content
Sovyron

OCI Generative AI

8 modelsProvider docs

As of Nov 16, 2026, OCI Generative AI lists 8 supported models in the Sovyron catalog, including Grok 4.6, Grok 4.3, Grok 4.20 (Non-Reasoning), Grok 4.20 (Reasoning) and GPT OSS 120B across the grok, gpt-oss and llama families. The cheapest rate in the table is GPT OSS 20B at $0.3 per 1M output tokens, the priciest Grok 4.6 at $6. On a 3:1 input:output blend the metered rates span $0.1275–$3 per 1M tokens, and every price is OCI Generative 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

8 of 8 models
OCI Generative AI model prices in USD per 1M tokens, updated Nov 16, 2026
Model1M input1M output1M cache readContextReleased
Grok 4.6$2$6$0.5500kAug 12, 2026
Grok 4.3$1.25$2.5$0.21.0MApr 17, 2026
Grok 4.20 (Non-Reasoning)$1.25$2.5$0.21.0MMar 9, 2026
Grok 4.20 (Reasoning)$1.25$2.5$0.21.0MMar 9, 2026
GPT OSS 120B$0.15$0.6—128kAug 5, 2025
GPT OSS 20B$0.07$0.3—128kAug 5, 2025
Llama 4 Maverick 17B Instruct$0.72$0.72—512kApr 5, 2025
Llama 4 Scout 17B Instruct$0.72$0.72—192kApr 5, 2025