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

26/119

Models

5/15

Providers

Vision Models (filtered)

Tool-enabled (filtered)

Free Models (filtered)


deepseek	deepseek-r1	$5.00	$10.00	—
deepseek	deepseek-v4-pro-0817	$1.01	$3.03	$0.03
deepseek	deepseek-v4-pro-0813	$1.18	$3.55	$0.12
deepseek	deepseek-v4-flash-vision-exp-0817	$0.56	$1.68	$0.02
deepseek	deepseek-v4-flash-0817	$0.34	$1.01	$0.01
deepseek	deepseek-v4-flash-0731-new	$0.45	$1.34	$0.04
deepseek	deepseek-r1-distill-qwen-32b	$0.12	$0.12	—
deepseek	deepseek-v4.1-flash	$0.33	$1.31	$0.01
zai	glm-5.3-flash	$0.09	$0.32	$0.03
zai	glm-5.3	$0.92	$3.22	$0.23
zai	glm-5.2	$0.67	$2.35	$0.17
moonshot	kimi-k2.7-code	$0.75	$3.18	$0.17
minimax	minimax-m3	$0.39	$1.57	$0.08
alibaba	qwen3.6-35b-a3b	$0.21	$1.24	—
deepseek	deepseek-v4-pro	$1.57	$3.14	$0.13
deepseek	deepseek-v4-flash	$0.12	$1.22	$0.03
moonshot	kimi-k2.6	$0.85	$3.55	$0.17
zai	glm-5.1	$0.92	$2.96	$0.17
minimax	minimax-m2.7	$0.35	$1.38	$0.07
zai	glm-5-turbo	$1.14	$3.80	—
minimax	minimax-m2.5	$0.28	$1.10	$0.06
moonshot	kimi-k2.5	$0.47	$2.42	$0.14
deepseek	deepseek-v3.2	$0.25	$0.76	—
alibaba	qwen3-32b	$0.08	$0.27	—
alibaba	qwen3-coder-480b-a35b-instruct	$0.60	$1.20	—
deepseek	deepseek-v3	$0.19	$0.75	—

Open Source Models

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

Compare

26/119

Models

5/15

Providers

Vision Models (filtered)

Tool-enabled (filtered)

Free Models (filtered)


deepseek	deepseek-r1	$5.00	$10.00	—
deepseek	deepseek-v4-pro-0817	$1.01	$3.03	$0.03
deepseek	deepseek-v4-pro-0813	$1.18	$3.55	$0.12
deepseek	deepseek-v4-flash-vision-exp-0817	$0.56	$1.68	$0.02
deepseek	deepseek-v4-flash-0817	$0.34	$1.01	$0.01
deepseek	deepseek-v4-flash-0731-new	$0.45	$1.34	$0.04
deepseek	deepseek-r1-distill-qwen-32b	$0.12	$0.12	—
deepseek	deepseek-v4.1-flash	$0.33	$1.31	$0.01
zai	glm-5.3-flash	$0.09	$0.32	$0.03
zai	glm-5.3	$0.92	$3.22	$0.23
zai	glm-5.2	$0.67	$2.35	$0.17
moonshot	kimi-k2.7-code	$0.75	$3.18	$0.17
minimax	minimax-m3	$0.39	$1.57	$0.08
alibaba	qwen3.6-35b-a3b	$0.21	$1.24	—
deepseek	deepseek-v4-pro	$1.57	$3.14	$0.13
deepseek	deepseek-v4-flash	$0.12	$1.22	$0.03
moonshot	kimi-k2.6	$0.85	$3.55	$0.17
zai	glm-5.1	$0.92	$2.96	$0.17
minimax	minimax-m2.7	$0.35	$1.38	$0.07
zai	glm-5-turbo	$1.14	$3.80	—
minimax	minimax-m2.5	$0.28	$1.10	$0.06
moonshot	kimi-k2.5	$0.47	$2.42	$0.14
deepseek	deepseek-v3.2	$0.25	$0.76	—
alibaba	qwen3-32b	$0.08	$0.27	—
alibaba	qwen3-coder-480b-a35b-instruct	$0.60	$1.20	—
deepseek	deepseek-v3	$0.19	$0.75	—

Open Source Models

Support

Welcome!

Open Source Models

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?

Stay ahead of the curve