Best Free LLMs (2026)
Free-to-use large language models with open weights you can run locally or via free-tier APIs. Ranked by MMLU to surface the most capable free options first.
| # | Model | Input $/1M | Output $/1M | |
|---|---|---|---|---|
| 1 | Llama 3.1 405B | — | — | |
| 2 | DeepSeek V3 Tools | $0.10 | $0.28 | |
| 3 | Qwen2.5 72B | $0.20 | $0.60 | |
| 4 | Qwen2.5 32B Instruct | $0.15 | $0.15 | |
| 5 | Llama 3.1 70B Instruct | $0.40 | $0.40 | |
| 6 | Mixtral 8x22B v0.1 | GPU·hr | $1.00 | |
| 7 | Falcon 180B | — | — | |
| 8 | Qwen2.5 14B Instruct | $0.08 | $0.08 | |
| 9 | Qwen2 72B | $0.45 | $0.65 | |
| 10 | Mistral Large 2 VisionTools | $0.48 | $1.50 | |
| 11 | Gemma 2 27B Instruct | GPU·hr | $1.00 | |
| 12 | Llama 3 70B Instruct | $0.40 | $0.40 | |
| 13 | Mistral NeMo Instruct (2407) | GPU·hr | $1.00 | |
| 14 | Qwen2.5 7B Instruct | $0.04 | $0.04 | |
| 15 | Qwen2 7B | $0.05 | $0.15 | |
| 16 | Mixtral 8x7B | $0.15 | $0.20 | |
| 17 | Qwen1.5-72B | $0.65 | $0.90 | |
| 18 | DeepSeek Coder V2 Lite | $0.50 | $0.50 | |
| 19 | Mistral 7B Instruct v0.3 Tools | $0.20 | $0.20 | |
| 20 | Qwen1.5-110B | $1.50 | $1.80 |
Compare Top Picks
Browse Other Categories
Best LLMs for Code GenerationBest Open Source LLMsBest Multimodal / Vision LLMsBest LLMs for Reasoning & MathBest Small Language Models (SLMs)Best LLMs for Function Calling & Tool UseCheapest LLM APIsBest Long Context LLMsBest LLM APIsBest LLMs for EnterpriseBest LLMs for WritingBest LLMs for Customer Support