Gemini 3.6 Flash

LLM Provider / Model · High-throughput 1M-context work: long-context coding, computer use, agentic loops

At a glance

Input price	$1.50
Output price	$7.50
Cache price	$0.15
Price tier	Mid
Context window	1M+
Max output	64K
Context tier	500K+
Speed tier	Fast
Latency	fast
Knowledge cutoff	Mar 2026
Modality	Multimodal (vision, audio, video)
Model ID	gemini-3.6-flash
Provider	Google
Benchmark	Uses ~17% fewer output tokens than 3.5 Flash at higher coding scores
Released	Jul 2026
Hosting	Closed/API
Capabilities	Vision, Audio, Video, Tool use, Thinking, Streaming, Function calling, Prompt caching, Code execution

Vision, Audio, Video, Tool use, Thinking, Streaming, Function calling, Prompt caching, Code execution

High-throughput 1M-context work: long-context coding, computer use, agentic loops

Kiro's spec mode is tuned for Claude models — Gemini 3.6 Flash may work but spec-driven flows are best with Claude.
OpenAI Codex (VS Code) is tied to OpenAI's hosted GPT-5 and Codex models — Gemini 3.6 Flash is not selectable inside this integration.
Claude Code only works with Claude models — your LLM is Gemini 3.6 Flash.
Devin uses Cognition's proprietary model internally — your selected Gemini 3.6 Flash will be ignored.
OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected Gemini 3.6 Flash will be ignored.
The Claude Code SDK is tuned for Claude models — Gemini 3.6 Flash may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
Lovable uses a fixed internal model — your selected Gemini 3.6 Flash will be ignored.
Replit Agent 3 uses its own model selection internally — your selected Gemini 3.6 Flash will be ignored.

Build a full stack around Gemini 3.6 Flash — Flowpicker shows compatibility warnings before you commit.