Berget.AI
5 modelsProvider docs
As of Nov 18, 2026, Berget.AI lists 5 supported models in the Sovyron catalog, including GLM-5.3-Flash, Qwen3.8 27B, Kimi K3, Gemma 4 31B Instruct and Mistral Small 3.2 24B Instruct 2506 across the glm-flash, qwen, kimi-k3, gemma and mistral-small families. The cheapest rate in the table is Mistral Small 3.2 24B Instruct 2506 at $0.3365 per 1M output tokens, the priciest Kimi K3 at $16.8225. On a 3:1 input:output blend the metered rates span $0.3365–$6.729 per 1M tokens, and every price is Berget.AI'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
5 of 5 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| GLM-5.3-Flash | $0.29 | $0.58 | — | 1.0M | Aug 26, 2026 |
| Qwen3.8 27B | $0.46 | $3.48 | — | 262k | Aug 14, 2026 |
| Kimi K3 | $3.3645 | $16.8225 | $1.0093 | 328k | Jul 16, 2026 |
| Gemma 4 31B Instruct | $0.2804 | $0.5607 | — | 128k | Apr 2, 2026 |
| Mistral Small 3.2 24B Instruct 2506 | $0.3365 | $0.3365 | — | 32k | Jun 20, 2025 |