Skip to content
Sovyron

Powerspring

7 modelsProvider docs

As of Nov 22, 2026, Powerspring lists 7 supported models in the Sovyron catalog, including DeepSeek V4.1 Flash, GLM-5.3-Flash, Qwen3.8 27B, Gemma 4 26B A4B IT and Gemma 4 31B IT across the deepseek-flash, glm-flash, qwen, gemma and gpt-oss families. The cheapest rate in the table is GPT OSS 20B at $0.1658 per 1M output tokens, the priciest DeepSeek V4.1 Flash at $0.6348. On a 3:1 input:output blend the metered rates span $0.0746–$0.3171 per 1M tokens, and every price is Powerspring'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

7 of 7 models
Powerspring model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleased
DeepSeek V4.1 Flash$0.2112$0.6348$0.00581.0MSep 10, 2026
GLM-5.3-Flash$0.1044$0.3644$0.01861.0MAug 26, 2026
Qwen3.8 27B$0.1044$0.4166$0.04181.0MAug 14, 2026
Gemma 4 26B A4B IT$0.116$0.5802—262kApr 2, 2026
Gemma 4 31B IT$0.2321$0.4062—262kApr 2, 2026
GPT OSS 120B$0.0884$0.4421—131kAug 5, 2025
GPT OSS 20B$0.0442$0.1658—131kAug 5, 2025