Gemini 3.8 Flash

GOOGLE Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1497Chatbot Arena Verified

Max Context Limit1,048,576Max Out: 65,536 tokens

Prompt Caching90% OFF$0.07 / 1M cached

Standard API / 1M$4.50🧠 Deep Reasoner

Model Capabilities & Contract SLAs

Fictional
Drafting
Classification
Conversational
Reasoning
Agentic
Coding & Logic
📋 Strict JSON Schema
🛠️ Native Tool Calling
🧠 Extended Test-Time Reasoning

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.75 / 1M

⚡ Cached Input (Prompt Cache Read)90% OFF$0.07 / 1M

Output Tokens (Completion)$3.75 / 1M

Internal Reasoning Tokens$3.75 / 1M

Pricing data via OpenRouter. Sync: 10/2/2026

Evaluate Competitors

VS Engine MatchupGemini 3.8 Flash vs OpenAI: GPT-6 Astra VS Engine MatchupGemini 3.8 Flash vs Anthropic: Claude Fable 5.1 VS Engine MatchupGemini 3.8 Flash vs OpenAI: GPT-6 Astra (batch)VS Engine MatchupGemini 3.8 Flash vs Google: Gemini 3.6 Flash (batch)VS Engine MatchupGemini 3.8 Flash vs Anthropic: Claude Fable 5 (batch)VS Engine MatchupGemini 3.8 Flash vs OpenAI: GPT-5 Image