Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Google’s text & code models on Kyma — Gemini 3.8 Flash, Gemini 3.7 Flash, Gemini 3.5 Flash Lite and 6 more.
| Model ID | Best for | Per 1M |
|---|---|---|
gemini-3.8-flash | High-volume agentic and multimodal work at 1M context | $2.026 in · $10.126 out |
gemini-3.7-flash | High-volume multimodal work at 1M context where the reply itself is long | $2.026 in · $10.126 out |
gemini-3.5-flash-lite | High-volume classification, extraction and summarisation at 1M context | $0.405 in · $3.375 out |
gemini-3.6-flash | High-volume multimodal work at 1M context | $1.013 in · $5.063 out |
gemini-3.5-flash | Long context, multimodal, fast reasoning | $2.025 in · $12.15 out |
gemma-4-31b | Multimodal, vision, general | $0.0763 in · $0.218 out |
gemini-3.1-pro | Hard reasoning and long-horizon agentic work that Flash cannot carry | $2.70 in · $16.20 out |
gemini-3-flash | Long context, reasoning | $0.675 in · $4.05 out |
gemini-2.5-flash | Long context, fast | $0.405 in · $3.375 out |
gemini-2.5-flash is served until 2026-10-20. Move to another model before then.