Kitani
8 modelsProvider docs
As of Nov 22, 2026, Kitani lists 8 supported models in the Sovyron catalog, including DeepSeek V4.1 Flash 1017, GLM-5.3-Flash, GLM-5.3, DeepSeek V4 Pro 0813 and Gemma 4 12B IT across the deepseek-flash, glm-flash, glm, deepseek-pro, gemma and ministral families. The cheapest rate in the table is Llama-3.1-8B-Instruct at $0.0765 per 1M output tokens, the priciest GLM-5.3 at $4.25. On a 3:1 input:output blend the metered rates span $0.0558–$2.0375 per 1M tokens, and every price is Kitani'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 | $0.25 | $1.1 | $0.006 | 1.0M | Oct 17, 2026 |
| GLM-5.3-Flash | $0.15 | $0.5 | $0.03 | 1.0M | Aug 26, 2026 |
| GLM-5.3 | $1.3 | $4.25 | $0.26 | 1.0M | Aug 14, 2026 |
| DeepSeek V4 Pro 0813 | $1.2 | $3.8 | $0.044 | 1.0M | Aug 13, 2026 |
| Gemma 4 12B IT | $0.045 | $0.23 | $0.0225 | 8k | Jun 9, 2026 |
| Ministral 3 8B 2512 | $0.135 | $0.135 | $0.0675 | 8k | Dec 2, 2025 |
| Llama-3.1-8B-Instruct | $0.049 | $0.0765 | $0.0245 | 8k | Jul 23, 2024 |
| Mistral Nemo | $0.0903 | $0.1086 | $0.0451 | 8k | Jul 18, 2024 |