Skip to content
Sovyron

submodel

9 modelsProvider docs

As of Nov 22, 2026, submodel lists 9 supported models in the Sovyron catalog, including DeepSeek V3.1, GPT OSS 120B, GLM 4.5 FP8, GLM-4.5-Air and Qwen3 235B-A22B Thinking 2507 across the deepseek, gpt-oss, glm, glm-air, qwen and qwen-coder families. The cheapest rate in the table is Qwen3 235B A22B Instruct 2507 at $0.3 per 1M output tokens, the priciest DeepSeek V3 0324 at $0.8. On a 3:1 input:output blend the metered rates span $0.2–$0.35 per 1M tokens, and every price is submodel'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

9 of 9 models
submodel model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleased
DeepSeek V3.1$0.2$0.8—75kAug 21, 2025
GPT OSS 120B$0.1$0.5—131kAug 5, 2025
GLM 4.5 FP8$0.2$0.8—131kJul 28, 2025
GLM-4.5-Air$0.1$0.5—131kJul 28, 2025
Qwen3 235B-A22B Thinking 2507$0.2$0.6—262kJul 25, 2025
Qwen3-Coder 480B-A35B Instruct$0.2$0.8—262kJul 22, 2025
Qwen3 235B A22B Instruct 2507$0.2$0.3—262kJul 21, 2025
DeepSeek R1 0528$0.2$0.8—75kMay 28, 2025
DeepSeek V3 0324$0.2$0.8—75kMar 24, 2025