Gemma 3 27B
Gemma 3 27B by Google: 12 offers. From €0.072 per 1M input tokens, with EU processing from €0.089.
Calculate costs for this modelCompare offersView price history
Profile
| Profile | |
|---|---|
| Developer | |
| Type | Language models |
| Origin | US |
| Input types | text+bild |
| Context (tokens) | 131,072 |
| Max. output (tokens) | 117,964 |
| Reasoning | ohne |
| Parameters (bn) | 27.4 |
| Open weights | ✓ yes |
| Licence | Gemma Terms of Use |
| VRAM at 4-bit (GB) | 20 (RTX PRO 4000) |
| Released | – |
searchit Entity Extraction (24 Sept 2026): 25.2 %
Offers with processing in the EU (4)
| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---|---|---|---|
| cortecs | AT | standard | €0.089 | €0.27 | api.cortecs.ai | 14 Oct 2026 |
| Nebius Token Factory | NL | standard | €0.089 | €0.27 | tokenfactory.nebius.com | 14 Oct 2026 |
| HostYourAI | NL | standard | €0.10 | €0.32 | hostyourai.com | 14 Oct 2026 |
| Melious | DE | standard | €0.25 | €0.50 | melious.ai | 13 Oct 2026 |
€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.
Offers outside the EU (8)
| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---|---|---|---|
| DeepInfra | US | standard | €0.072 | €0.14 | deepinfra.com | 14 Oct 2026 |
| AWS Bedrock | US | flex | €0.11 | €0.17 | pricing.us-east-1.amazonaws.com | 14 Oct 2026 |
| Novita AI | US | standard | €0.11 | €0.18 | novita.ai | 13 Oct 2026 |
| Venice.ai | US | standard | €0.11 | €0.18 | docs.venice.ai | 14 Oct 2026 |
| Parasail | US | standard | €0.072 | €0.40 | www.parasail.io | 2 Oct 2026 |
| Parasail | US | serverless | €0.072 | €0.40 | www.parasail.io | 2 Oct 2026 |
| AWS Bedrock | US | standard | €0.21 | €0.34 | pricing.us-east-1.amazonaws.com | 14 Oct 2026 |
| AWS Bedrock | US | priority | €0.36 | €0.60 | pricing.us-east-1.amazonaws.com | 14 Oct 2026 |
€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.
AI Act
Whether the developer has signed the Code of Practice for general-purpose AI models: unknown. What this means is explained under “EU and AI Act”. EU processing and AI Act
Benchmarks
| Benchmarks | |
|---|---|
| GPQA Diamond (Artificial Analysis) | 42.8 |
| Humanity's Last Exam (Artificial Analysis) | 4.4 |
| Berkeley Function-Calling Leaderboard V4 | 29.5 |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 22.5 |
| Vectara HHEM-2.3 | 7.4 |
| Vectara HHEM-2.3 – antwortrate | 98.8 |
| Vectara HHEM-2.3 – halluzination | 7.4 |
| LLMStructBench: Benchmarking Large Language Model Structured Data Extraction (arXiv:2602.14743) | 0.74 |
| LLMStructBench: Benchmarking Large Language Model Structured Data Extraction (arXiv:2602.14743) – doc micro | 0.52 |
| LLMStructBench: Benchmarking Large Language Model Structured Data Extraction (arXiv:2602.14743) – f1 micro | 0.96 |
| LLMStructBench: Benchmarking Large Language Model Structured Data Extraction (arXiv:2602.14743) – score | 0.74 |
| MMMU-Pro (llm-stats-Abzug, Rang 1..50 von 69) | 0.5 |
| MÖVE (Bundesdruckerei), arXiv 2606.13111 – themen | 0.65 |
| SWE-bench Pro Public (Scale AI) | 11.4 |
| searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer beziehungen | 5.4 |
| searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer entitaeten | 45 |
| Structured Output Benchmark (SOB), arXiv 2604.25359 | 0.97 |
| Structured Output Benchmark (SOB), arXiv 2604.25359 – json pass | 0.97 |
| Structured Output Benchmark (SOB), arXiv 2604.25359 – wertgenauigkeit | 0.8 |
| MMLU-Pro (TIGER-Lab Leaderboard) | 67.5 |