Skip to content
Sovyron

Tinfoil

9 modelsProvider docs

As of Nov 22, 2026, Tinfoil lists 9 supported models in the Sovyron catalog, including Inkling 2 Small, Kimi K3.1 Pro, DeepSeek V4.1 Flash, GLM-5.3 and Gemma 4 31B IT across the inkling-small, kimi-pro, deepseek-flash, glm, gemma and gpt-oss-safeguard families. The cheapest rate in the table is GPT OSS Safeguard 120B at $0.6 per 1M output tokens, the priciest Kimi K3.1 Pro at $20. On a 3:1 input:output blend the metered rates span $0.012–$8 per 1M tokens, and every price is Tinfoil'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
Tinfoil model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleased
Inkling 2 Small$0.3$1$0.03524kNov 5, 2026
Kimi K3.1 Pro$4$20$0.4262kOct 23, 2026
DeepSeek V4.1 Flash$0.6$1.45$0.011.0MSep 10, 2026
GLM-5.3$1.8$5.75$0.451.0MAug 14, 2026
Gemma 4 31B IT$0.4$1—262kApr 2, 2026
GPT OSS Safeguard 120B$0.15$0.6—131kOct 29, 2025
GPT OSS 120B$0.15$0.6—131kAug 5, 2025
Llama-3.3-70B-Instruct$1.75$2.75—131kDec 6, 2024
Nomic Embed Text v1.5$0.016free—8kFeb 1, 2024