AKI.IO
7 modelsProvider docs
As of Oct 4, 2026, AKI.IO lists 7 supported models in the Sovyron catalog, including GLM-5.3, Qwen3.8 27B, DeepSeek V4 Flash 0731, Qwen3.6 35B-A3B and Gemma 4 26B A4B IT — glm, qwen, deepseek-flash, gemma, mistral-small and gpt-oss families. Its metered rates span $0.2–$1.625 per 1M tokens on a 3:1 input:output blend, and every price in the table is AKI.IO's own, normalized to USD — open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
7 of 7 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| GLM-5.3 | $1 | $3.5 | $0.25 | 524k | Aug 14, 2026 |
| Qwen3.8 27B | $0.3 | $2.2 | $0.1 | 262k | Aug 14, 2026 |
| DeepSeek V4 Flash 0731 | $0.2 | $0.5 | $0.1 | 1.0M | Jul 31, 2026 |
| Qwen3.6 35B-A3B | $0.15 | $0.5 | — | 256k | Apr 17, 2026 |
| Gemma 4 26B A4B IT | $0.1 | $0.5 | — | 256k | Apr 2, 2026 |
| Mistral Small 4 | $0.2 | $0.6 | — | 262k | Mar 16, 2026 |
| GPT OSS 120B | $0.15 | $0.55 | — | 128k | Aug 5, 2025 |