Inference APIs
11 modelsProvider docs
As of Nov 22, 2026, Inference APIs lists 11 supported models in the Sovyron catalog, including DeepSeek V4.1 Flash, GLM-5.3-Flash, Qwen3.8 Flash, GLM-5.3 and Kimi K2.7 Code across the deepseek-flash, glm-flash, qwen-flash, glm, kimi-code and minimax-m families. The cheapest rate in the table is GPT OSS 20B at $0.19 per 1M output tokens, the priciest GLM-5.3 at $5.72. On a 3:1 input:output blend the metered rates span $0.0775–$2.795 per 1M tokens, and every price is Inference APIs'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 | $0.4 | $1.6 | $0.01 | 1.0M | Sep 10, 2026 |
| GLM-5.3-Flash | $0.2 | $0.66 | $0.04 | 1.0M | Aug 26, 2026 |
| Qwen3.8 Flash | $0.15 | $0.5 | $0.02 | 1.0M | Aug 26, 2026 |
| GLM-5.3 | $1.82 | $5.72 | $0.34 | 1.0M | Aug 14, 2026 |
| Kimi K2.7 Code | $0.89 | $4.42 | $0.18 | 262k | Jun 12, 2026 |
| MiniMax-M3 | $0.39 | $1.56 | $0.08 | 524k | Jun 1, 2026 |
| DeepSeek V4 Flash | $0.19 | $0.38 | $0.04 | 1.0M | Apr 24, 2026 |
| DeepSeek V4 Pro | $1.72 | $5.15 | $0.17 | 1.0M | Apr 24, 2026 |
| GPT OSS 120B | $0.2 | $0.8 | — | 131k | Aug 5, 2025 |
| GPT OSS 20B | $0.04 | $0.19 | — | 131k | Aug 5, 2025 |
| Llama-3.3-70B-Instruct | $0.2 | $0.5 | — | 131k | Dec 6, 2024 |