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
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | $0.2791 | $1.1165 | $0.1116 | 1.0M | Oct 17, 2026 |
| Kolibri 1 | $0.1675 | $0.6141 | $0.0837 | 262k | Oct 3, 2026 |
| DeepSeek V4.1 Flash | $0.2804 | $1.1215 | $0.1121 | 1.0M | Sep 10, 2026 |
| GLM-5.3 | $1.1215 | $3.9253 | $0.2804 | 524k | Aug 14, 2026 |
| Qwen3.8 27B | $0.1675 | $0.7257 | $0.0837 | 262k | Aug 14, 2026 |
| Gemma 4 26B A4B IT | $0.1121 | $0.5607 | — | 256k | Apr 2, 2026 |
| Mistral Small 4 | $0.2243 | $0.6729 | — | 262k | Mar 16, 2026 |
| GPT OSS 120B | $0.1682 | $0.6168 | — | 128k | Aug 5, 2025 |