Skip to content
Sovyron

IO.NET

11 modelsProvider docs

As of Nov 22, 2026, IO.NET lists 11 supported models in the Sovyron catalog, including Kimi K2 Thinking, GLM-4.6, Kimi K2 Instruct, Qwen 3 Next 80B Instruct and GPT OSS 120B across the kimi, glm, qwen, gpt-oss, qwen-coder and deepseek-r families. The cheapest rate in the table is Mistral Nemo Instruct 2407 at $0.082 per 1M output tokens, the priciest Kimi K2 Thinking at $2.5. On a 3:1 input:output blend the metered rates span $0.0591–$1.075 per 1M tokens, and every price is IO.NET'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

11 of 11 models
IO.NET model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleased
Kimi K2 Thinking$0.6$2.5$0.333kNov 6, 2025
GLM-4.6$0.52$2.0375$0.26200kSep 30, 2025
Kimi K2 Instruct$0.57$2.3$0.28533kSep 5, 2025
Qwen 3 Next 80B Instruct$0.1187$1.2625$0.0594262kSep 1, 2025
GPT OSS 120B$0.188$0.7$0.094131kAug 5, 2025
GPT OSS 20B$0.055$0.194$0.027564kAug 5, 2025
Qwen 3 Coder 480B$0.4612$2.2938$0.2306106kJul 22, 2025
DeepSeek R1$0.5237$2.2053$0.2618128kMay 28, 2025
Llama 4 Maverick 17B 128E Instruct$0.2687$0.8263$0.1344430kApr 5, 2025
Llama-3.3-70B-Instruct$0.5466$1.0226$0.2733128kDec 6, 2024
Mistral Nemo Instruct 2407$0.0514$0.082$0.0257128kJul 18, 2024