Gemini 3.5 Flash Official Specifications, Pricing & Benchmarks
Gemini 3.5 Flash (gemini-3.5-flash) by Google DeepMind, released 2026-05-19, featuring 1,048,576 context window, 65,536 max output tokens, and Text+Image+Video+Audio+PDF input.
📋 Gemini 3.5 Flash Official API & System Card Specifications
Verified against official Google DeepMind developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- gemini-3.5-flash
- Release Date
- 2026-05-19
- Weight License
- Proprietary (Undisclosed)
- Native Reasoning
- ✅ Supported
- Function Calling & JSON Schema
- ✅ 原生支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 1,049,000 tokens (1049K)
- Max Output Tokens
- 65,536 tokens
- Input Modalities
- Text + Image + Video + Audio + PDF
- Output Modalities
- Text
- Direct China Access
- 🌐 Global / OpenRouter
- Deployment Mode
- Cloud API only (Proprietary)
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 1.5
- Cached Input / 1M
- $ 0.15 -90%
- Output / 1M Tokens
- $ 9
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 Gemini 3.5 Flash Full Benchmark Scorecard
19 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 4 items
MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.
Terminal-Bench 2.0 is an updated benchmark for testing AI agents' tool use ability to operate a computer via terminal.
SWE-Bench Pro is an advanced version of SWE-Bench that evaluates language models on complex, real-world software engineering tasks requiring extended reasoning and multi-step problem solving.
DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.
🤖 Agents & Tools 6 items
OSWorld-Verified is a verified subset of OSWorld, a scalable real computer environment for multimodal agents supporting task setup, execution-based evaluation, and interactive learning across Ubuntu, Windows, and macOS.
Finance Agent is a benchmark for evaluating AI models on agentic financial analysis tasks, testing their ability to process financial data, perform calculations, and generate accurate analyses across various financial domains.
Finance Agent v2 is an agentic financial-analysis benchmark from Vals that evaluates models on real-world finance workflows, measuring their ability to retrieve and reason over financial documents, perform multi-step calculations, and produce accurate analyses.
Tool Decathlon is a comprehensive benchmark for evaluating AI agents' ability to use multiple tools across diverse task categories. It measures proficiency in tool selection, sequencing, and execution across ten different tool-use scenarios.
Blueprint-Bench 2 is an agentic spatial reasoning benchmark that evaluates a model's ability to understand, plan, and reason over architectural blueprints and other structured spatial documents. Scores are reported as a normalized score.
The Legal Agent Benchmark (LAB) is Harvey's open-source benchmark for evaluating AI agents on complex, long-horizon legal work.
📐 Math 2 items
LiveBench is a challenging, contamination-limited LLM benchmark that addresses test set contamination by releasing new questions monthly based on recently-released datasets, arXiv papers, news articles, and IMDb movie synopses.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions.
👁️ Multimodal 3 items
CharXiv-R is the reasoning component of the CharXiv benchmark, focusing on complex reasoning questions that require synthesizing information across visual chart elements.
A more robust multi-discipline multimodal understanding benchmark that enhances MMMU through a three-step process: filtering text-only answerable questions, augmenting candidate options, and introducing vision-only input settings.
ARC-AGI-2 is an upgraded benchmark for measuring abstract reasoning and problem-solving abilities in AI systems through visual grid transformation tasks.
📜 Long Context 2 items
MRCR v2 (8-needle) is a variant of the Multi-Round Coreference Resolution benchmark that includes 8 needle items to retrieve from long contexts. This tests models' ability to simultaneously track and reason about multiple pieces of information across extended conversations.
MRCR v2 (Multi-Round Coreference Resolution version 2) is an enhanced version of the synthetic long-context reasoning task.
🧠 Reasoning & Science 2 items
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
MultiChallenge is a realistic multi-turn conversation evaluation benchmark that challenges frontier LLMs across four key categories: instruction retention (maintaining instructions throughout conversations), inference memory (recalling and connecting details from previous…
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to Gemini 3.5 Flash
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is Gemini 3.5 Flash open-source or proprietary?
Gemini 3.5 Flash (gemini-3.5-flash) is a proprietary commercial model by Google DeepMind. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.
What are the context limit and API pricing of Gemini 3.5 Flash?
Gemini 3.5 Flash supports 1049K input context and 65,536 max output tokens, priced at $1.5/1M input ($0.15/1M cached) and $9/1M output.