Gemma 2 von Google ist ein leistungsstarkes KI-Modell mit einem Kontextfenster von 8K Token zu API-Preisen von $0/1M Input- und $0/1M Output-Token für Softwareentwicklung, Analyse und Enterprise-Workflows.
Technical Specifications
- Provider
- Category
- open-source
- Release Date
- 2024-06
- Batch API Discount
- Standard rate
- Consumer Subscription
- Free / Self-Hosted
- Reasoning Effort Control
- Fixed
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- models/gemma-2
- Supported SDK & API Protocol
- Google Gemini API (generateContent) + OpenAI-Compatible SDK
- Lifecycle & Deprecation Status
- Legacy Stable (Upgrade path available in Google lineup)
- Production Rate Limits (RPM & TPM)
- Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
- Long-Context Pricing Tier (>128K / >200K)
- Free across full context window (only KV-cache VRAM scales)
- Prompt Cache Write & TTL Policy
- Automatic prefix KV-caching in vLLM / SGLang (0 cost)
- Computer Use & Browser GUI Agent
- API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
- MCP & Parallel Tool Calling
- Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
- Web Search Grounding & Code Sandbox
- Built-in Google Search Grounding + Managed Python Code Execution Sandbox
- Fine-Tuning & Distillation Support
- Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token)
- Weights Precision & Quantization
- BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
- Minimum GPU VRAM Requirement
- 2 GB VRAM (4-bit Quantized) · 4 GB VRAM (Native BF16)
- Supported Inference Engines
- vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
- System Card & Safety Framework
- Google DeepMind Frontier Safety Framework Verified
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Gemma 2 Cost, Context, Hardware & API Integration
Open-weights or free-tier model: $0 API license cost when self-hosted.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Gemma 2:
Benchmark Scores & 6-Axis Capability Radar
- MMLU-Pro
- 68.5%
- HumanEval
- 72%
- Chatbot Arena Elo
- 1250pts
Strengths
- Fortschrittliche Dense transformer with sliding window attention and soft-capping-Architektur von Google mit 8K Token Kontextfenster
- Starkes Preis-Leistungs-Verhältnis ($0/1M Input, $0/1M Output) bei hoher Durchsatzrate
- Hohe Präzision bei Code-Generierung, logischem Schließen und mehrsprachigen Benchmarks
Limitations & Trade-offs
- Bei sehr großen Kontextmengen ist eine sorgfältige Token-Budgetierung ratsam
- Spezialisierte Fachaufgaben profitieren von gezieltem Prompt-Engineering
Editorial Assessment
Gemma 2 von Google überzeugt durch eine ausgewogene Kombination aus Intelligenz, Geschwindigkeit und Kosteneffizienz.
Best for: Unternehmensautomatisierung, Software-Engineering, autonome KI-Agenten und Google-Produktionssysteme
Compare Gemma 2
Frequently Asked Questions about Gemma 2
How much does the Gemma 2 API cost per 1M tokens?+
Gemma 2 by Google is priced at $0 per 1M input tokens and $0 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0 per 1M tokens, and asynchronous Batch API requests receive a 0% discount.
Should I use a $20/month subscription or the Gemma 2 pay-as-you-go API?+
A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.
How many words and pages fit in Gemma 2's context window?+
Gemma 2 features a 8K tokens context window, which equals approximately 6,144 English words or ~16 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 4,096 tokens.
Can I run Gemma 2 locally on my own GPU (Open Weights)?+
Yes, Gemma 2 (2B / 9B / 27B) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.
Does Google train on data sent to the Gemma 2 API, and is commercial use allowed?+
100% Isolated when self-hosted on private GPUs or VPC. License tier: Open-Weights Research & Commercial License. Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.
How does Gemma 2 perform on coding and reasoning benchmarks?+
Gemma 2 achieves a composite Intelligence Index of 58/100, scoring N/A% on SWE-bench Verified, N/A% on GPQA Diamond, 68.5% on MMLU-Pro, and 1250 pts on Chatbot Arena Elo.
What is Gemma 2 best used for?+
Gemma 2 is best suited for: Unternehmensautomatisierung, Software-Engineering, autonome KI-Agenten und Google-Produktionssysteme. Assessment: Gemma 2 von Google überzeugt durch eine ausgewogene Kombination aus Intelligenz, Geschwindigkeit und Kosteneffizienz.
Google Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to Google's flagship reasoning tier:
Gemini 4 Argon
Gemini 3.8 Flash
Gemini 3.7 Flash
Gemini 3.6 Flash
Gemini 3.5 Flash-Lite
Gemini Omni Flash
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to Gemma 2:
The basic unit of text that a language model processes, typically representing about 3 to 4 English characters or roughly 0.75 words. For example, the sentence "Artificial intelligence is fast" breaks down into about 5 tokens.
A standardized evaluation suite used to objectively measure and rank an AI model's capabilities across specific tasks — such as SWE-bench Verified for software engineering, AIME for competitive math, or MMLU for general knowledge.
The maximum number of tokens a model can consider at once — both the input it reads and the output it writes. A 1,000,000-token context window can hold roughly 750,000 English words in a single request.
The ability of a language model to recognize when an external capability is needed and output structured JSON arguments to invoke external APIs, databases, or terminal commands. The runtime executes the tool and passes results back to the model.
An open standard created by Anthropic that allows AI applications and agents to connect seamlessly to local filesystems, development environments, and third-party APIs via standardized server interfaces.
The neural network architecture introduced in 2017 that powers modern LLMs, using self-attention mechanisms to process all tokens in a sequence concurrently rather than sequentially.
Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.
Offizielle Quellen: Google DeepMind Gemma 2 Report↗