Gemini 3.8 Flash Official Specifications, Pricing & Benchmarks
High-speed native omni-modal Flash model ($0.75/$3.75) handling hours of video/audio and huge PDFs.
📋 Gemini 3.8 Flash Official API & System Card Specifications
Verified against official Google DeepMind developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- gemini-3.8-flash
- Release Date
- 2026-09-02
- 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
- 1,048,000 tokens (1048K)
- 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
- $ 0.75
- Cached Input / 1M
- $ 0.075 -90%
- Output / 1M Tokens
- $ 3.75
- Tiered Pricing Notes
- Free tier available in Google AI Studio; implicit & explicit caching at $0.075/1M
🏆 Official Benchmark Results
Sourced from official System Card / Model Card & technical reports
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks.
PhD-level Google-proof science reasoning questions
LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code.
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.
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 Gemini 3.8 Flash Full Benchmark Scorecard
13 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 3 items
Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal.
DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.
Terminal-Bench 4.0 evaluates AI agents on real-world work in terminal and command-line containerized environments across 66 tasks, with emphasis on science-adjacent and frontier engineering problems.
🤖 Agents & Tools 5 items
LABBench2 evaluates models on real-world biology research tasks.
Vals Finance Agent v2 evaluates AI agents on realistic financial analyst tasks.
OSWorld 2.0 is a benchmark of 108 long-horizon, real-world computer-use workflows spanning everyday and professional tasks.
GDPval-AA evaluates AI agents on economically valuable professional knowledge-work tasks and reports performance as an Elo score.
Harvey's Legal Agent Benchmark evaluates AI agents on complex legal workflows and reports the all-pass rate.
👁️ Multimodal 3 items
LVBench is an extreme long video understanding benchmark designed to evaluate multimodal models on videos up to two hours in duration. It contains 6 major categories and 21 subcategories, with videos averaging five times longer than existing datasets.
CharXiv-R is the reasoning component of the CharXiv benchmark, focusing on complex reasoning questions that require synthesizing information across visual chart elements.
GDP.pdf is a knowledge-work vision benchmark that evaluates models on economically valuable professional tasks presented as visual documents (PDFs), testing document-based reasoning, chart and table interpretation, and problem solving without tools.
🧠 Reasoning & Science 2 items
BioMysteryBench evaluates a model's ability to reason through challenging molecular biology problems, reporting performance on a hard subset and on the subset of problems solved by human experts.
HLE-Verified evaluates multidisciplinary expert reasoning on a verified subset of Humanity's Last Exam.
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to Gemini 3.8 Flash
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is Gemini 3.8 Flash open-source or proprietary?
Gemini 3.8 Flash (gemini-3.8-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 3.8 Flash?
Gemini 3.8 Flash supports 1048K input context and 65,536 max output tokens, priced at $0.75/1M input ($0.075/1M cached) and $3.75/1M output.