Llama 3.3 70B
Llama 3.3 70B by Meta: 17 offers. From €0.12 per 1M input tokens, with EU processing from €0.63.
Calculate costs for this modelCompare offersView price history
Profile
| Profile | |
|---|---|
| Developer | Meta |
| Type | Language models |
| Origin | US |
| Input types | text |
| Context (tokens) | 128,000 |
| Max. output (tokens) | 16,384 |
| Reasoning | ohne |
| Parameters (bn) | 70.6 |
| Open weights | ✓ yes |
| Licence | Llama 3.3 Community License |
| VRAM at 4-bit (GB) | 43 (RTX PRO 5000) |
| Released | 7 Oct 2025 |
searchit Entity Extraction (24 Sept 2026): 12.6 %
Offers with processing in the EU (7)
| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---|---|---|---|
| IONOS AI Model Hub | DE | standard | €0.63 | €0.63 | cloud.ionos.com | 6 Oct 2026 |
| cortecs | AT | standard | €0.65 | €0.65 | api.cortecs.ai | 14 Oct 2026 |
| OVHcloud | FR | standard | €0.67 | €0.67 | www.ovhcloud.com | 13 Oct 2026 |
| Scaleway | FR | standard | €0.90 | €0.90 | www.scaleway.com | 13 Oct 2026 |
| evroc | SE | standard | €1.00 | €1.00 | evroc.com | 8 Oct 2026 |
| HostYourAI | NL | standard | €1.04 | €1.04 | hostyourai.com | 14 Oct 2026 |
| GreenPT | NL | standard | €1.10 | €1.10 | docs.greenpt.ai | 12 Oct 2026 |
€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.
Offers outside the EU (10)
| Provider | Country | Variant | Input | Output | Source | As of |
|---|---|---|---|---|---|---|
| Novita AI | US | standard | €0.12 | €0.36 | novita.ai | 13 Oct 2026 |
| Google Vertex AI | US | batch | €0.32 | €0.32 | cloud.google.com | 14 Oct 2026 |
| Parasail | US | standard | €0.20 | €0.45 | www.parasail.io | 2 Oct 2026 |
| Parasail | US | serverless | €0.20 | €0.45 | www.parasail.io | 2 Oct 2026 |
| AWS Bedrock | US | standard | €0.64 | €0.64 | pricing.us-east-1.amazonaws.com | 14 Oct 2026 |
| Google Vertex AI | US | standard | €0.64 | €0.64 | cloud.google.com | 14 Oct 2026 |
| io.net | US | standard | €0.49 | €0.91 | api.intelligence.io.solutions | 14 Oct 2026 |
| SambaNova (SambaCloud) | US | standard | €0.54 | €1.07 | api.sambanova.ai | 12 Oct 2026 |
| Infercom | DE | standard | €0.60 | €1.20 | infercom.ai | 2 Oct 2026 |
| Venice.ai | US | standard | €0.63 | €2.50 | docs.venice.ai | 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) | 49.8 |
| Humanity's Last Exam (Artificial Analysis) | 3.6 |
| Berkeley Function-Calling Leaderboard V4 | 31.9 |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 5.1 |
| Vectara HHEM-2.3 | 4.1 |
| Vectara HHEM-2.3 – antwortrate | 99.5 |
| Vectara HHEM-2.3 – halluzination | 4.1 |
| LiveBench (Aufgabensatz 2026-01-08) | 50.16 |
| LLMStructBench: Benchmarking Large Language Model Structured Data Extraction (arXiv:2602.14743) | 0.7 |
| LLMStructBench: Benchmarking Large Language Model Structured Data Extraction (arXiv:2602.14743) – doc micro | 0.45 |
| LLMStructBench: Benchmarking Large Language Model Structured Data Extraction (arXiv:2602.14743) – f1 micro | 0.95 |
| LLMStructBench: Benchmarking Large Language Model Structured Data Extraction (arXiv:2602.14743) – score | 0.7 |
| MÖVE (Bundesdruckerei), arXiv 2606.13111 | 0.77 |
| MÖVE (Bundesdruckerei), arXiv 2606.13111 – qa | 0.69 |
| MÖVE (Bundesdruckerei), arXiv 2606.13111 – themen | 0.64 |
| MÖVE (Bundesdruckerei), arXiv 2606.13111 – zusammenfassung | 0.77 |
| 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 | 19.8 |
| MMLU-Pro (TIGER-Lab Leaderboard) | 65.9 |