Skip to content
Sovyron

AKI.IO

8 modelsProvider docs

As of Nov 22, 2026, AKI.IO lists 8 supported models in the Sovyron catalog, including DeepSeek V4.1 Flash 1017, Kolibri 1, DeepSeek V4.1 Flash, GLM-5.3 and Qwen3.8 27B across the deepseek-flash, kolibri, glm, qwen, gemma and mistral-small families. The cheapest rate in the table is Gemma 4 26B A4B IT at $0.5607 per 1M output tokens, the priciest GLM-5.3 at $3.9253. On a 3:1 input:output blend the metered rates span $0.2243–$1.8224 per 1M tokens, and every price is AKI.IO'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

8 of 8 models
AKI.IO model prices in USD per 1M tokens, updated Nov 22, 2026
Model1M input1M output1M cache readContextReleased
DeepSeek V4.1 Flash 1017$0.2791$1.1165$0.11161.0MOct 17, 2026
Kolibri 1$0.1675$0.6141$0.0837262kOct 3, 2026
DeepSeek V4.1 Flash$0.2804$1.1215$0.11211.0MSep 10, 2026
GLM-5.3$1.1215$3.9253$0.2804524kAug 14, 2026
Qwen3.8 27B$0.1675$0.7257$0.0837262kAug 14, 2026
Gemma 4 26B A4B IT$0.1121$0.5607—256kApr 2, 2026
Mistral Small 4$0.2243$0.6729—262kMar 16, 2026
GPT OSS 120B$0.1682$0.6168—128kAug 5, 2025