Skip to content
Sovyron

routing.run

15 modelsProvider docs

As of Nov 22, 2026, routing.run lists 15 supported models in the Sovyron catalog, including GPT-5.6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, GLM 5.2 Nitro and GLM-5.2 across the gpt-luna, gpt-sol, gpt-terra, glm, kimi-code and nemotron-ultra families. The cheapest rate in the table is Nemotron 3 Ultra 550B A55B at $0.1 per 1M output tokens, the priciest Claude Opus 4.8 at $25. On a 3:1 input:output blend the metered rates span $0.1–$10 per 1M tokens, and every price is routing.run'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

15 of 15 models
routing.run model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleased
GPT-5.6 Luna$0.7$4.2—1.0MJul 9, 2026
GPT-5.6 Sol$2.5$15—1.0MJul 9, 2026
GPT-5.6 Terra$1.5$9—1.0MJul 9, 2026
GLM 5.2 Nitro$0.8$2.4—200kJun 13, 2026
GLM-5.2$0.8$2.4—200kJun 13, 2026
Kimi K2.7 Code$0.275$1.1—200kJun 12, 2026
Kimi K2.7 Code Nitro$0.275$1.1—200kJun 12, 2026
Nemotron 3 Ultra 550B A55B$0.1$0.1—131kJun 4, 2026
Claude Opus 4.8$5$25—1.0MMay 28, 2026
DeepSeek V4 Flash$0.112$0.224—1.0MApr 24, 2026
DeepSeek V4 Pro$0.348$0.696—1.0MApr 24, 2026
Kimi K2.6$0.275$1.1—200kApr 20, 2026
Kimi K2.6 Nitro$0.275$1.1—200kApr 20, 2026
Qwen3.5 9B$0.16$0.48—262kFeb 23, 2026
Claude Sonnet 4.6$3$15—1.0MFeb 17, 2026