Liquid Inference
8 modelsProvider docs
As of Nov 22, 2026, Liquid Inference lists 8 supported models in the Sovyron catalog, including Kimi K3.1 Pro, Liquid Auto, DeepSeek V4.1 Flash 1017, DeepSeek V4.1 Flash and GLM-5.3-Flash across the kimi-pro, auto, deepseek-flash, glm-flash, glm and qwen families. The cheapest rate in the table is DeepSeek V4.1 Flash 1017 at $0.206 per 1M output tokens, the priciest Kimi K3 at $10.2. On a 3:1 input:output blend the metered rates span $0.0958–$3.495 per 1M tokens, and every price is Liquid Inference'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 |
|---|---|---|---|---|---|
| Kimi K3.1 Pro | $2.18 | $5.46 | $1.23 | 1.0M | Oct 23, 2026 |
| Liquid Auto | — | — | — | 10.0M | Oct 20, 2026 |
| DeepSeek V4.1 Flash 1017 | $0.059 | $0.206 | $0.0026 | 1.0M | Oct 17, 2026 |
| DeepSeek V4.1 Flash | $0.0868 | $0.21 | $0.007 | 1.0M | Sep 10, 2026 |
| GLM-5.3-Flash | $0.112 | $0.315 | $0.0278 | 1.0M | Aug 26, 2026 |
| GLM-5.3 | $0.84 | $3.1 | $0.195 | 1.0M | Aug 14, 2026 |
| Qwen3.8 27B | $0.08 | $0.525 | $0.0525 | 262k | Aug 14, 2026 |
| Kimi K3 | $1.26 | $10.2 | $0.315 | 1.0M | Jul 16, 2026 |