As of Nov 22, 2026, Phase Router lists 2 supported models in the Sovyron catalog, including GPT OSS 120B and Qwen3-Coder 480B-A35B Instruct across the gpt-oss and qwen-coder families. The cheapest rate in the table is GPT OSS 120B at $0.1768 per 1M output tokens, the priciest Qwen3-Coder 480B-A35B Instruct at $1.04. On a 3:1 input:output blend the metered rates span $0.0731–$0.494 per 1M tokens, and every price is Phase Router'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
2 of 2 models
Phase Router model prices in USD per 1M tokens, updated Nov 22, 2026