Skip to content
Sovyron

STACKIT

6 modelsProvider docs

As of Nov 22, 2026, STACKIT lists 6 supported models in the Sovyron catalog, including Qwen3-VL Embedding 8B, Qwen3 VL 235B, GPT OSS 120B, GPT OSS 20B and Llama 3.3 70B across the qwen-embedding, qwen-vl, gpt-oss, llama and mistral families. The cheapest rate in the table is GPT OSS 20B at $0.29 per 1M output tokens, the priciest Qwen3 VL 235B at $2.05. On a 3:1 input:output blend the metered rates span $0.0168–$1.8325 per 1M tokens, and every price is STACKIT'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

6 of 6 models
STACKIT model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleased
Qwen3-VL Embedding 8B$0.09free—32kFeb 5, 2026
Qwen3 VL 235B$1.76$2.05—218kSep 23, 2025
GPT OSS 120B$0.53$0.76—131kAug 5, 2025
GPT OSS 20B$0.18$0.29—131kAug 5, 2025
Llama 3.3 70B$0.53$0.76—128kDec 6, 2024
E5 Mistral 7B$0.0224free—4kDec 11, 2023