September 24, 2026
You can code with Gemini 3.8 Flash in Cline for free: 41 points in the rankings
On Sep 24, Gemini 3.8 Flash scored 41 points and 291 tokens/s in Artificial Analysis, and Cline opened free access to it. On that index it beats GPT-5.6 Luna, DeepSeek v4.1 Flash and Qwen3.8.
Cline
@cline
Gemini 3.8 Flash is now free in Cline. It scores 41 points on the Artificial Analysis Intelligence Index—the best result among models in its price range. 291 tokens/s, a 1 million-token context window, and stronger benchmark results than GPT-5.6 Luna, DeepSeek v4.1 Flash, and Qwen3.8.
· 60.2K views
Google released Gemini on Sep 2. Until Dec 31, 2026 a million input and output tokens cost $0.75 and $3.75; from Jan 1, 2027 the prices rise to $1.50 and $7.50. In Cline the model is free up to a limit, after which the interface shows the reset time.
Working with code. Gemini 3.8 Flash holds 1M tokens of context, returns up to 64K tokens per response and reasons at low, medium and high effort. In Cline, pick Cline Provider and find the model by searching `free`: the free options carry a FREE tag.
Google promises gains over Gemini 3.7 Flash on software engineering and agentic tasks at the same input price. To spend less compute, the company suggests low effort or the previous model.
Starting Jan 1, 2027, Gemini 3.8 Flash API prices will double.
Source
