RunInfra
7 modelsProvider docs
As of Oct 4, 2026, RunInfra lists 7 supported models in the Sovyron catalog, including GLM-5.3-Flash, Ornith 1.5 35B A3B, Qwen3.8 27B, DeepSeek V4 Pro 0813 and Qwen3.8 2.4T A95B (NVFP4) — glm-flash, ornith, qwen, deepseek-thinking, nemotron and deepseek-flash families. Its metered rates span $0.075–$3 per 1M tokens on a 3:1 input:output blend, and every price in the table is RunInfra'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-Flash | $0.1 | $0.4 | $0.01 | 1.0M | Aug 26, 2026 |
| Ornith 1.5 35B A3B | $0.1 | $0.4 | $0.01 | 262k | Aug 18, 2026 |
| Qwen3.8 27B | $0.1 | $0.4 | $0.01 | 262k | Aug 14, 2026 |
| DeepSeek V4 Pro 0813 | $0.6 | $1.9 | $0.03 | 1.0M | Aug 12, 2026 |
| Qwen3.8 2.4T A95B (NVFP4) | $2 | $6 | $0.2 | 262k | Aug 12, 2026 |
| Nemotron 3.5 Lightning 30B A3B | $0.05 | $0.15 | $0.01 | 262k | Aug 11, 2026 |
| DeepSeek V4 Flash 0731 | $0.13 | $0.27 | $0.01 | 1.0M | Jul 31, 2026 |