What is the best open source LLM?

DeepSeek V4, Qwen3.7, GLM-5.2, Kimi K2.6, and MiniMax M3 are the current leaders, each within striking distance of proprietary frontier models. For smaller, hardware-friendly options, GPT-OSS 20B, Gemma 4, and Qwen3.5 9B are the standouts.

What does 'open source' mean for LLMs?

Usually 'open weight': the trained weights are downloadable, but licenses vary — some are Apache 2.0 or MIT, others (like the Llama license) carry usage restrictions, and training data is rarely published. Check the license of a specific model before building on it.

Should I self-host or use an API?

Self-hosting pays off with steady high volume, strict data-residency needs, or fine-tuned weights. For everything else, per-token APIs are cheaper than idle GPUs. A middle path: develop against hosted open models and keep self-hosting as an exit option, since the weights are public.

Are open models cheaper than proprietary ones?

Dramatically, per token. Competition among hosts drives prices down — DeepSeek V4 Flash and Qwen3 Coder 30B cost 10–50x less than frontier proprietary models. The list above shows every provider's price for each model.

Open Source Models

Open-weight models — Llama, DeepSeek, Qwen, GLM, Kimi, GPT-OSS, Gemma, and more — served through one API

Compare

Models

Providers

Vision Models

Tool-enabled

Free Models


S OpenRouter	glm-4.7-flash	$0.06	$0.40	—
EmberCloud	glm-4.7-flash	$0.06	$0.40	$0.01
Z AI	glm-4.7-flashx	$0.07	$0.40	$0.01
S OpenRouter	glm-4.7	$0.40	$1.75	$0.08
ByteDance	glm-4.7	$0.60	$2.20	$0.11
Cerebras	glm-4.7	$2.25	$2.75	—
Vertex AI (OpenAI-compatible)	glm-4.7	$0.60	$2.20	—
Z AI	glm-4.7	$0.60	$2.20	$0.11
Together AI	glm-4.7	$0.45	$2.00	—
EmberCloud	glm-4.7	$0.38	$1.98	$0.19
S Hormouz	glm-4.7	$0.60	$2.20	$0.11
S Metis	glm-4.7	$0.60	$2.20	$0.11
NovitaAI	glm-4.7	$0.60	$2.20	$0.11
Z AI	glm-4.5-airx	$1.10	$4.50	$0.22
Z AI	glm-4.5-x	$2.20	$8.90	$0.45
S OpenRouter	glm-4.5-air	$0.13	$0.85	$0.02
EmberCloud	glm-4.5-air	$0.13	$0.85	$0.02
Z AI	glm-4.5-air	$0.20	$1.10	$0.03
S OpenRouter	glm-4.5v	$0.60	$1.80	$0.11
NovitaAI	glm-4.5v	$0.60	$1.80	$0.11
Z AI	glm-4.5v	$0.60	$1.80	$0.11
EmberCloud	glm-4.5	$0.60	$2.20	$0.11
Z AI	glm-4.5	$0.60	$2.20	$0.11
S OpenRouter	glm-4.5	$0.60	$2.20	$0.11
S AvalAI	qwen2-5-vl-32b-instruct	$1.40	$4.20	$0.70
S OpenRouter	qwen3-vl-235b-a22b-thinking	$0.26	$2.60	—
NovitaAI	qwen3-vl-235b-a22b-thinking	$0.98	$3.95	—
DeepInfra	qwen3-vl-235b-a22b-instruct	$0.20	$0.88	$0.11
S OpenRouter	qwen3-vl-235b-a22b-instruct	$0.21	$1.90	$0.10
NovitaAI	qwen3-vl-235b-a22b-instruct	$0.30	$1.50	—
S OpenRouter	qwen3-vl-30b-a3b-thinking	$0.13	$1.56	—
DeepInfra	qwen3-vl-30b-a3b-instruct	$0.15	$0.60	—
NovitaAI	qwen3-vl-30b-a3b-instruct	$0.20	$0.70	—
S OpenRouter	qwen3-vl-30b-a3b-instruct	$0.13	$0.52	—
S OpenRouter	qwen3-next-80b-a3b-instruct	$0.10	$1.10	$0.07
Vertex AI (OpenAI-compatible)	qwen3-next-80b-a3b-instruct	$0.15	$1.20	—
S AvalAI	qwen3-next-80b-a3b-instruct	$0.14	$0.57	$0.07
NovitaAI	qwen3-next-80b-a3b-instruct	$0.15	$1.50	—
Vertex AI (OpenAI-compatible)	qwen3-next-80b-a3b-thinking	$0.15	$1.20	—
S AvalAI	qwen3-next-80b-a3b-thinking	$0.14	$1.43	$0.07
Nebius AI	qwen3-next-80b-a3b-thinking	$0.15	$1.20	—
S OpenRouter	qwen3-next-80b-a3b-thinking	$0.10	$0.78	—
S AvalAI	qwen3-30b-a3b-instruct-2507	$0.20	$0.80	$0.10
Nebius AI	qwen3-30b-a3b-instruct-2507	$0.10	$0.30	—
S OpenRouter	qwen3-30b-a3b-instruct-2507	$0.10	$0.30	—
NovitaAI	qwen3-coder-30b-a3b-instruct	$0.07	$0.27	—
S OpenRouter	qwen3-coder-30b-a3b-instruct	$0.07	$0.27	—
S AvalAI	qwen3-coder-480b-a35b-instruct	$1.50	$7.50	$0.15
Vertex AI (OpenAI-compatible)	qwen3-coder-480b-a35b-instruct	$0.22	$1.80	$0.02
S GapGPT	qwen3-coder-480b-a35b-instruct	$3.00	$12.00	—

Open Source Models

Stay ahead of the curve

Open Source Models

Stay ahead of the curve

Frequently asked questions

What is the best open source LLM?

What does 'open source' mean for LLMs?

Should I self-host or use an API?

Are open models cheaper than proprietary ones?