Runcrate
11 modelsProvider docs
As of Nov 22, 2026, Runcrate lists 11 supported models in the Sovyron catalog, including DeepSeek V4.1 Flash 1017, DeepSeek V4.1 Flash, GLM-5.3-Flash, Qwen3.8 Flash and GLM-5.3 across the deepseek-flash, glm-flash, qwen-flash, glm, kimi and deepseek families. The cheapest rate in the table is GPT OSS 120B at $0.1785 per 1M output tokens, the priciest Kimi K2.6 at $3.675. On a 3:1 input:output blend the metered rates span $0.0738–$1.5094 per 1M tokens, and every price is Runcrate'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
11 of 11 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | $0.1029 | $0.3087 | $0.0031 | 1.0M | Oct 17, 2026 |
| DeepSeek V4.1 Flash | $0.147 | $0.441 | $0.0044 | 1.0M | Sep 10, 2026 |
| GLM-5.3-Flash | $0.1575 | $0.525 | $0.0315 | 1.0M | Aug 26, 2026 |
| Qwen3.8 Flash | $0.1187 | $0.4011 | $0.0148 | 1.0M | Aug 26, 2026 |
| GLM-5.3 | $0.5906 | $2.625 | $0.1313 | 1.0M | Aug 14, 2026 |
| Kimi K2.6 | $0.7875 | $3.675 | $0.1575 | 262k | Apr 20, 2026 |
| DeepSeek V3.2 | $0.273 | $0.399 | $0.1365 | 164k | Dec 1, 2025 |
| GPT OSS 120B | $0.0389 | $0.1785 | $0.0058 | 131k | Aug 5, 2025 |
| Qwen3-Coder 480B-A35B Instruct | $0.315 | $1.05 | $0.105 | 262k | Jul 22, 2025 |
| Qwen3 235B A22B Instruct 2507 | $0.0945 | $0.5775 | — | 262k | Jul 21, 2025 |
| Llama 3.3 70B Instruct Turbo | $0.105 | $0.336 | — | 131k | Dec 6, 2024 |