Skip to content
Sovyron

SambaNova

4 modelsProvider docs

As of Nov 22, 2026, SambaNova lists 4 supported models in the Sovyron catalog, including MiniMax-M3.1-Flash, GLM-5.3, Gemma 4 31B IT and GPT OSS 120B across the minimax-m-flash, glm, gemma and gpt-oss families. The cheapest rate in the table is GPT OSS 120B at $0.59 per 1M output tokens, the priciest GLM-5.3 at $8.8. On a 3:1 input:output blend the metered rates span $0.3125–$4.3 per 1M tokens, and every price is SambaNova'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

4 of 4 models
SambaNova model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleased
MiniMax-M3.1-Flash$0.3$1.2$0.031.0MOct 19, 2026
GLM-5.3$2.8$8.8$0.141.0MAug 14, 2026
Gemma 4 31B IT$0.38$1.15—131kApr 2, 2026
GPT OSS 120B$0.22$0.59—131kAug 5, 2025