Is it cheaper to self-host or use an API?

At low volume, API is cheaper. At very high volume (24/7 high utilization), self-hosting wins. The crossover point is usually around 10 to 100 million tokens per day depending on model size. Our self-host estimates above assume on-demand cloud GPUs.

Where do I download the weights?

HuggingFace is the canonical source for nearly every OSS model. Check the model detail page on BenchGecko for the exact HF ID.

Which OSS models are safe for commercial use?

Apache 2.0 and MIT licensed models (Mistral, most Qwen versions, Gemma) are clean for commercial use. Llama Community License has revenue-threshold restrictions. Always read the specific license before shipping.

Can I fine-tune an OSS model?

Yes, if the license permits (most do). Fine-tuning services on Together, Fireworks, and DeepInfra run $1 to $5 per million training tokens. Deploy the fine-tune back on the same platform or download the adapter.

Licensing · Open source

Open source LLM pricing

Every open-source LLM with license, cheapest API provider, and rough self-host cost. Weights on HuggingFace, API on OpenRouter, DeepInfra, Together, Fireworks, or self-host.

Models243

Cheapest API$0.00

LicensesApache · MIT · Custom

All pricing Pricing home

What this page is

This page lists every open-source LLM with priced API access. For each, we show the license, cheapest API on the market, and a rough self-host cost estimate based on parameter count. Weights are downloadable from HuggingFace. APIs are offered by OpenRouter, DeepInfra, Together, Fireworks, Groq, Cerebras, and others. For very high volume, self-hosting on reserved GPUs is cheaper; for anything under 100M tokens per day, API access usually wins on total cost.

Open source models · ranked by API price

Cheapest input price first.

#	Model	License	Cheapest API	Params	Self-host est	Weights
1	Gemma 3 12B (free)	Custom OSS	$0.00/M	-	-	-
2	Gemma 3 27B (free)	Custom OSS	$0.00/M	-	-	-
3	Gemma 3 4B (free)	Custom OSS	$0.00/M	-	-	-
4	Gemma 3n 2B (free)	Custom OSS	$0.00/M	-	-	-
5	Gemma 3n 4B (free)	Custom OSS	$0.00/M	-	-	-
6	Gemma 4 26B A4B (free)	Apache 2.0	$0.00/M	26B	~$1.50/hr (1x A100)	HF
7	Gemma 4 31B (free)	Apache 2.0	$0.00/M	31B	~$1.50/hr (1x A100)	HF
8	GLM 4.5 Air (free)	Custom OSS	$0.00/M	-	-	-
9	gpt-oss-120b (free)	Custom OSS	$0.00/M	-	-	-
10	gpt-oss-20b (free)	Custom OSS	$0.00/M	-	-	-
11	Hermes 3 405B Instruct (free)	Custom OSS	$0.00/M	-	-	-
12	Laguna M.1 (free)	Custom OSS	$0.00/M	-	-	-
13	Laguna XS.2 (free)	Custom OSS	$0.00/M	-	-	-
14	LFM2.5-1.2B-Instruct (free)	Custom OSS	$0.00/M	-	-	-
15	LFM2.5-1.2B-Thinking (free)	Custom OSS	$0.00/M	-	-	-
16	Llama 3.2 3B Instruct (free)	Custom OSS	$0.00/M	-	-	-
17	Llama 3.3 70B Instruct (free)	Custom OSS	$0.00/M	-	-	-
18	MiniMax M2.5 (free)	Custom OSS	$0.00/M	-	-	-
19	Mistral Small 3.1 24B (free)	Custom OSS	$0.00/M	-	-	-
20	Nemotron 3 Nano 30B A3B (free)	Custom OSS	$0.00/M	-	-	-
21	Nemotron 3 Nano Omni (free)	other	$0.00/M	33B	~$1.50/hr (1x A100)	HF
22	Nemotron 3 Super (free)	other	$0.00/M	124B	~$12/hr (4x A100)	HF
23	Nemotron 3 Ultra (free)	other	$0.00/M	561B	~$60+/hr (multi-node)	HF
24	Nemotron 3.5 Content Safety (free)	other	$0.00/M	4B	~$0.50/hr (1x L4)	HF
25	Nemotron Nano 12B 2 VL (free)	Custom OSS	$0.00/M	-	-	-
26	Nemotron Nano 9B V2 (free)	Custom OSS	$0.00/M	-	-	-
27	Nex-N2-Pro (free)	Custom OSS	$0.00/M	-	-	-
28	North Mini Code (free)	Apache 2.0	$0.00/M	30B	~$1.50/hr (1x A100)	HF
29	Qwen3 4B (free)	Custom OSS	$0.00/M	-	-	-
30	Qwen3 Coder 480B A35B (free)	Custom OSS	$0.00/M	-	-	-
31	Qwen3 Next 80B A3B Instruct (free)	Custom OSS	$0.00/M	-	-	-
32	Qwen3.6 Plus Preview (free)	Custom OSS	$0.00/M	-	-	-
33	Step 3.5 Flash (free)	Custom OSS	$0.00/M	-	-	-
34	Trinity Large Preview (free)	Custom OSS	$0.00/M	-	-	-
35	Trinity Mini (free)	Custom OSS	$0.00/M	-	-	-
36	Uncensored (free)	Custom OSS	$0.00/M	-	-	-
37	LFM2-2.6B	Custom OSS	$0.01/M	-	-	-
38	LFM2-8B-A1B	Custom OSS	$0.01/M	-	-	-
39	Granite 4.0 Micro	Apache 2.0	$0.02/M	3B	~$0.50/hr (1x L4)	HF
40	gpt-oss-20b	Apache 2.0	$0.02/M	21B	~$1.50/hr (1x A100)	HF
41	Mistral Nemo	Apache 2.0	$0.02/M	12B	~$1.50/hr (1x A100)	HF
42	Llama 3.1 8B Instruct	Llama Community	$0.02/M	8B	~$0.50/hr (1x L4)	HF
43	DeepSeek V4 Flash	MIT	$0.03/M	291B	~$30/hr (8x H100)	HF
44	Llama 3.2 1B Instruct	Llama Community	$0.03/M	1B	~$0.50/hr (1x L4)	HF
45	Gemma 2 9B	Custom OSS	$0.03/M	-	-	-
46	LFM2-24B-A2B	Custom OSS	$0.03/M	-	-	-
47	Qwen2.5 Coder 7B Instruct	Custom OSS	$0.03/M	-	-	-
48	Qwen-Turbo	Custom OSS	$0.03/M	-	-	-
49	gpt-oss-120b	Apache 2.0	$0.04/M	117B	~$12/hr (4x A100)	HF
50	Llama 3 8B Lunaris	Llama Community	$0.04/M	8B	~$0.50/hr (1x L4)	HF
51	Nemotron Nano 9B V2	Custom OSS	$0.04/M	-	-	-
52	Trinity Mini	Custom OSS	$0.04/M	-	-	-
53	Qwen3 30B A3B Instruct 2507	Apache 2.0	$0.05/M	31B	~$1.50/hr (1x A100)	HF
54	Gemma 3 12B	Gemma License	$0.05/M	12B	~$1.50/hr (1x A100)	HF
55	Gemma 3 4B	Gemma License	$0.05/M	4B	~$0.50/hr (1x L4)	HF
56	Granite 4.1 8B	Custom OSS	$0.05/M	-	-	-
57	Llama 3.2 3B Instruct	Llama Community	$0.05/M	3B	~$0.50/hr (1x L4)	HF
58	Mistral Small 3	Apache 2.0	$0.05/M	24B	~$1.50/hr (1x A100)	HF
59	Nemotron 3 Nano 30B A3B	other	$0.05/M	32B	~$1.50/hr (1x A100)	HF
60	Olmo 2 32B Instruct	Custom OSS	$0.05/M	-	-	-
61	Gemma 3n 4B	Custom OSS	$0.06/M	-	-	-
62	GLM 4.7 Flash	MIT	$0.06/M	31B	~$1.50/hr (1x A100)	HF
63	Hy3 preview	other	$0.06/M	299B	~$30/hr (8x H100)	HF
64	Qwen3.5-Flash	Custom OSS	$0.07/M	-	-	-
65	Gemma 4 26B A4B	Apache 2.0	$0.07/M	26B	~$1.50/hr (1x A100)	HF
66	ERNIE 4.5 21B A3B	Custom OSS	$0.07/M	-	-	-
67	ERNIE 4.5 21B A3B Thinking	Custom OSS	$0.07/M	-	-	-
68	Phi 4	MIT	$0.07/M	15B	~$1.50/hr (1x A100)	HF
69	Qwen3 Coder 30B A3B Instruct	Apache 2.0	$0.07/M	31B	~$1.50/hr (1x A100)	HF
70	gpt-oss-safeguard-20b	Apache 2.0	$0.07/M	22B	~$1.50/hr (1x A100)	HF
71	Gemma 3 27B	Gemma License	$0.08/M	27B	~$1.50/hr (1x A100)	HF
72	MythoMax 13B	other	$0.08/M	-	-	HF
73	Nemotron 3 Super	other	$0.08/M	124B	~$12/hr (4x A100)	HF
74	Phi 4 Mini Instruct	Custom OSS	$0.08/M	-	-	-
75	Qwen3 32B	Apache 2.0	$0.08/M	33B	~$1.50/hr (1x A100)	HF
76	Gemma 4 31B	Apache 2.0	$0.09/M	31B	~$1.50/hr (1x A100)	HF
77	MiMo-V2-Flash	Custom OSS	$0.09/M	-	-	-
78	Qwen3 235B A22B Instruct 2507	Apache 2.0	$0.09/M	235B	~$30/hr (8x H100)	HF
79	Qwen3 Next 80B A3B Instruct	Apache 2.0	$0.09/M	81B	~$12/hr (4x A100)	HF
80	Tongyi DeepResearch 30B A3B	Custom OSS	$0.09/M	-	-	-
81	Mistral Small 3.2 24B	Apache 2.0	$0.09/M	24B	~$1.50/hr (1x A100)	HF
82	Devstral Small 1.1	Custom OSS	$0.10/M	-	-	-
83	Laguna XS.2	Custom OSS	$0.10/M	-	-	-
84	Llama 3.3 70B Instruct	Llama Community	$0.10/M	71B	~$4/hr (2x A100)	HF
85	Llama 4 Scout	other	$0.10/M	109B	~$12/hr (4x A100)	HF
86	Ministral 3 3B 2512	Apache 2.0	$0.10/M	4B	~$0.50/hr (1x L4)	HF
87	Mistral Small Creative	Custom OSS	$0.10/M	-	-	-
88	Qwen2.5 7B Instruct	Apache 2.0	$0.10/M	8B	~$0.50/hr (1x L4)	HF
89	Qwen3.5-9B	Apache 2.0	$0.10/M	10B	~$0.50/hr (1x L4)	HF
90	Reka Edge	other	$0.10/M	7B	~$0.50/hr (1x L4)	HF
91	Reka Flash 3	Apache 2.0	$0.10/M	21B	~$1.50/hr (1x A100)	HF
92	Step 3.5 Flash	Apache 2.0	$0.10/M	199B	~$12/hr (4x A100)	HF
93	UI-TARS 7B	Apache 2.0	$0.10/M	8B	~$0.50/hr (1x L4)	HF
94	Voxtral Small 24B 2507	Apache 2.0	$0.10/M	24B	~$1.50/hr (1x A100)	HF
95	Qwen3 VL 32B Instruct	Apache 2.0	$0.10/M	33B	~$1.50/hr (1x A100)	HF
96	Mistral 7B Instruct v0.1	Custom OSS	$0.11/M	-	-	-
97	Qwen3 8B	Apache 2.0	$0.12/M	8B	~$0.50/hr (1x L4)	HF
98	Qwen3 VL 8B Instruct	Apache 2.0	$0.12/M	9B	~$0.50/hr (1x L4)	HF
99	Qwen3 14B	Apache 2.0	$0.12/M	15B	~$1.50/hr (1x A100)	HF
100	Qwen3 30B A3B	Apache 2.0	$0.12/M	31B	~$1.50/hr (1x A100)	HF
101	Qwen3 Coder Next	Apache 2.0	$0.12/M	80B	~$4/hr (2x A100)	HF
102	GLM 4.5 Air	MIT	$0.13/M	110B	~$12/hr (4x A100)	HF
103	Hermes 4 70B	Custom OSS	$0.13/M	-	-	-
104	DeepSeek V3.1 Nex N1	Custom OSS	$0.14/M	-	-	-
105	Qwen VL Plus	Custom OSS	$0.14/M	-	-	-
106	ERNIE 4.5 VL 28B A3B	Custom OSS	$0.14/M	-	-	-
107	Hermes 2 Pro - Llama-3 8B	Custom OSS	$0.14/M	-	-	-
108	Hunyuan A13B Instruct	other	$0.14/M	80B	~$12/hr (4x A100)	HF
109	Llama 3 8B Instruct	Custom OSS	$0.14/M	-	-	-
110	MiMo-V2.5	MIT	$0.14/M	311B	~$30/hr (8x H100)	HF
111	Ministral 3 8B 2512	Apache 2.0	$0.15/M	9B	~$0.50/hr (1x L4)	HF
112	Mistral Small 4	Apache 2.0	$0.15/M	119B	~$12/hr (4x A100)	HF
113	Olmo 3 32B Think	Custom OSS	$0.15/M	-	-	-
114	Olmo 3.1 32B Think	Custom OSS	$0.15/M	-	-	-
115	Qwen3 Next 80B A3B Thinking	Apache 2.0	$0.15/M	81B	~$12/hr (4x A100)	HF
116	Qwen3 VL 30B A3B Instruct	Apache 2.0	$0.15/M	31B	~$1.50/hr (1x A100)	HF
117	Qwen3.5-35B-A3B	Apache 2.0	$0.15/M	36B	~$4/hr (2x A100)	HF
118	Qwen3.6 35B A3B	Apache 2.0	$0.15/M	36B	~$4/hr (2x A100)	HF
119	QwQ 32B	Custom OSS	$0.15/M	-	-	-
120	Rnj 1 Instruct	Custom OSS	$0.15/M	-	-	-
121	Llama Guard 4 12B	other	$0.18/M	12B	~$1.50/hr (1x A100)	HF
122	Qwen3 VL 8B Thinking	Apache 2.0	$0.18/M	9B	~$0.50/hr (1x L4)	HF
123	Llama 4 Maverick	other	$0.19/M	402B	~$30/hr (8x H100)	HF
124	Qwen3.6 Flash	Custom OSS	$0.19/M	-	-	-
125	Qwen3 Coder Flash	Custom OSS	$0.20/M	-	-	-
126	Qwen3.5-27B	Apache 2.0	$0.20/M	28B	~$1.50/hr (1x A100)	HF
127	INTELLECT-3	Custom OSS	$0.20/M	-	-	-
128	Laguna M.1	Custom OSS	$0.20/M	-	-	-
129	LongCat Flash Chat	Custom OSS	$0.20/M	-	-	-
130	MiniMax-01	Custom OSS	$0.20/M	456B	~$30/hr (8x H100)	HF
131	Ministral 3 14B 2512	Apache 2.0	$0.20/M	14B	~$1.50/hr (1x A100)	HF
132	Nemotron Nano 12B 2 VL	Custom OSS	$0.20/M	-	-	-
133	Olmo 3.1 32B Instruct	Custom OSS	$0.20/M	-	-	-
134	Qwen2.5 VL 32B Instruct	Custom OSS	$0.20/M	-	-	-
135	Qwen3 30B A3B Thinking 2507	Apache 2.0	$0.20/M	31B	~$1.50/hr (1x A100)	HF
136	Qwen3 VL 30B A3B Thinking	Apache 2.0	$0.20/M	31B	~$1.50/hr (1x A100)	HF
137	Saba	Custom OSS	$0.20/M	-	-	-
138	Step 3.7 Flash	Apache 2.0	$0.20/M	201B	~$30/hr (8x H100)	HF
139	DeepSeek V4 Pro	MIT	$0.21/M	1.6T	~$60+/hr (multi-node)	HF
140	MiniMax M2.7	other	$0.21/M	229B	~$30/hr (8x H100)	HF
141	Qwen3 VL 235B A22B Instruct	Apache 2.0	$0.21/M	236B	~$30/hr (8x H100)	HF
142	Qwen3 235B A22B Thinking 2507	Apache 2.0	$0.23/M	235B	~$30/hr (8x H100)	HF
143	DeepSeek V3 0324	MIT	$0.25/M	685B	~$60+/hr (multi-node)	HF
144	DeepSeek V3.1	MIT	$0.25/M	685B	~$60+/hr (multi-node)	HF
145	Rocinante 12B	Custom OSS	$0.25/M	-	-	-
146	Trinity Large Thinking	other	$0.25/M	399B	~$30/hr (8x H100)	HF
147	DeepSeek V3	Custom OSS	$0.26/M	685B	~$60+/hr (multi-node)	HF
148	Qwen Plus 0728	Custom OSS	$0.26/M	-	-	-
149	Qwen Plus 0728 (thinking)	Custom OSS	$0.26/M	-	-	-
150	Qwen-Plus	Custom OSS	$0.26/M	-	-	-
151	Qwen3.5 Plus 2026-02-15	Custom OSS	$0.26/M	-	-	-
152	Qwen3.5-122B-A10B	Apache 2.0	$0.26/M	125B	~$12/hr (4x A100)	HF
153	DeepSeek V3.1 Terminus	MIT	$0.27/M	685B	~$60+/hr (multi-node)	HF
154	DeepSeek V3.2 Exp	MIT	$0.27/M	685B	~$60+/hr (multi-node)	HF
155	MiniMax M2.5	other	$0.27/M	229B	~$30/hr (8x H100)	HF
156	DeepSeek V3.2	MIT	$0.28/M	685B	~$60+/hr (multi-node)	HF
157	ERNIE 4.5 300B A47B	Custom OSS	$0.28/M	-	-	-
158	R1 Distill Qwen 32B	Custom OSS	$0.29/M	-	-	-
159	Codestral 2508	Custom OSS	$0.30/M	-	-	-
160	Cydonia 24B V4.1	Custom OSS	$0.30/M	24B	~$1.50/hr (1x A100)	HF
161	DeepSeek R1T2 Chimera	Custom OSS	$0.30/M	-	-	-
162	GLM 4.6V	MIT	$0.30/M	108B	~$12/hr (4x A100)	HF
163	MiniMax M2	other	$0.30/M	229B	~$30/hr (8x H100)	HF
164	MiniMax M2.1	other	$0.30/M	229B	~$30/hr (8x H100)	HF
165	MiniMax M3	other	$0.30/M	427B	~$30/hr (8x H100)	HF
166	Qwen3 Coder 480B A35B	Apache 2.0	$0.30/M	480B	~$30/hr (8x H100)	HF
167	Qwen3.5 Plus 2026-04-20	Custom OSS	$0.30/M	-	-	-
168	Qwen3.6 27B	Apache 2.0	$0.32/M	28B	~$1.50/hr (1x A100)	HF
169	Qwen3.7 Plus	Custom OSS	$0.32/M	-	-	-
170	Qwen3.6 Plus	Custom OSS	$0.33/M	-	-	-
171	Llama 3.2 11B Vision Instruct	Custom OSS	$0.34/M	-	-	-
172	ReMM SLERP 13B	CC BY	$0.35/M	-	-	HF
173	Mistral Small 3.1 24B	Apache 2.0	$0.35/M	24B	~$1.50/hr (1x A100)	HF
174	Qwen2.5 72B Instruct	other	$0.36/M	73B	~$4/hr (2x A100)	HF
175	DeepSeek V3.2 Speciale	Custom OSS	$0.40/M	-	-	-
176	Devstral 2 2512	other	$0.40/M	125B	~$12/hr (4x A100)	HF
177	Devstral Medium	Custom OSS	$0.40/M	-	-	-
178	Llama 3.1 70B Instruct	Llama Community	$0.40/M	71B	~$4/hr (2x A100)	HF
179	Llama 3.3 Nemotron Super 49B V1.5	Custom OSS	$0.40/M	-	-	-
180	Mistral Medium 3	Custom OSS	$0.40/M	-	-	-
181	Mistral Medium 3.1	Custom OSS	$0.40/M	-	-	-
182	Qwen3 VL 235B A22B Thinking	Apache 2.0	$0.40/M	236B	~$30/hr (8x H100)	HF
183	UnslopNemo 12B	Custom OSS	$0.40/M	12B	~$1.50/hr (1x A100)	HF
184	ERNIE 4.5 VL 424B A47B	Apache 2.0	$0.42/M	424B	~$30/hr (8x H100)	HF
185	GLM 4.6	MIT	$0.43/M	357B	~$30/hr (8x H100)	HF
186	MiMo-V2.5-Pro	MIT	$0.43/M	1.0T	~$60+/hr (multi-node)	HF
187	Kimi K2.5	other	$0.45/M	1.0T	~$60+/hr (multi-node)	HF
188	Qwen3 235B A22B	Apache 2.0	$0.46/M	235B	~$30/hr (8x H100)	HF
189	Llama Guard 3 8B	Custom OSS	$0.48/M	-	-	-
190	Mistral Large 3 2512	Custom OSS	$0.50/M	-	-	-
191	Nemotron 3 Ultra	other	$0.50/M	561B	~$60+/hr (multi-node)	HF
192	Nex-N2-Pro	Custom OSS	$0.50/M	-	-	-
193	R1 0528	MIT	$0.50/M	685B	~$60+/hr (multi-node)	HF
194	Llama 3 70B Instruct	Custom OSS	$0.51/M	-	-	-
195	Qwen VL Max	Custom OSS	$0.52/M	-	-	-
196	Mixtral 8x7B Instruct	Custom OSS	$0.54/M	-	-	-
197	Qwen3.5 397B A17B	Apache 2.0	$0.55/M	403B	~$30/hr (8x H100)	HF
198	Skyfall 36B V2	other	$0.55/M	37B	~$4/hr (2x A100)	HF
199	Kimi K2 0711	other	$0.57/M	1.0T	~$60+/hr (multi-node)	HF
200	GLM 4.5	MIT	$0.60/M	358B	~$30/hr (8x H100)	HF
201	GLM 4.5V	MIT	$0.60/M	108B	~$12/hr (4x A100)	HF
202	GLM 4.7	MIT	$0.60/M	358B	~$30/hr (8x H100)	HF
203	GLM 5	MIT	$0.60/M	754B	~$60+/hr (multi-node)	HF
204	Kimi K2 0905	other	$0.60/M	1.0T	~$60+/hr (multi-node)	HF
205	Kimi K2 Thinking	other	$0.60/M	1.0T	~$60+/hr (multi-node)	HF
206	Llama 3.1 Nemotron Ultra 253B v1	Custom OSS	$0.60/M	-	-	-
207	Kimi K2.7 Code	other	$0.61/M	1.0T	~$60+/hr (multi-node)	HF
208	WizardLM-2 8x22B	Custom OSS	$0.62/M	-	-	-
209	Gemma 2 27B	Gemma License	$0.65/M	27B	~$1.50/hr (1x A100)	HF
210	Llama 3.3 Euryale 70B	Llama Community	$0.65/M	71B	~$4/hr (2x A100)	HF
211	Qwen3 Coder Plus	Custom OSS	$0.65/M	-	-	-
212	Qwen2.5 Coder 32B Instruct	Apache 2.0	$0.66/M	33B	~$1.50/hr (1x A100)	HF
213	Aion-1.0-Mini	Custom OSS	$0.70/M	-	-	-
214	Hermes 3 70B Instruct	Llama Community	$0.70/M	71B	~$4/hr (2x A100)	HF
215	R1	MIT	$0.70/M	684B	~$60+/hr (multi-node)	HF
216	Qwen3 Max	Custom OSS	$0.78/M	-	-	-
217	Qwen3 Max Thinking	Custom OSS	$0.78/M	-	-	-
218	CodeLLaMa 7B Instruct Solidity	Custom OSS	$0.80/M	-	-	-
219	Llemma 7b	Custom OSS	$0.80/M	-	-	-
220	Qwen2.5 VL 72B Instruct	other	$0.80/M	73B	~$4/hr (2x A100)	HF
221	R1 Distill Llama 70B	Custom OSS	$0.80/M	-	-	-
222	Llama 3.1 Euryale 70B v2.2	CC BY	$0.85/M	-	-	HF
223	Kimi K2.6	other	$0.95/M	1.0T	~$60+/hr (multi-node)	HF
224	GLM 5.1	MIT	$0.97/M	754B	~$60+/hr (multi-node)	HF
225	GLM 5.2	MIT	$1.00/M	753B	~$60+/hr (multi-node)	HF
226	Hermes 3 405B Instruct	Llama Community	$1.00/M	406B	~$30/hr (8x H100)	HF
227	Hermes 4 405B	Llama Community	$1.00/M	406B	~$30/hr (8x H100)	HF
228	Qwen3.6 Max Preview	Custom OSS	$1.03/M	-	-	-
229	Qwen-Max	Custom OSS	$1.04/M	-	-	-
230	Llama 3.1 Nemotron 70B Instruct	Custom OSS	$1.20/M	-	-	-
231	Qwen3.7 Max	Custom OSS	$1.25/M	-	-	-
232	Llama 3 Euryale 70B v2.1	Custom OSS	$1.48/M	-	-	-
233	Mistral Medium 3.5	Custom OSS	$1.50/M	-	-	-
234	Jamba Large 1.7	Custom OSS	$2.00/M	-	-	-
235	Mistral Large	Custom OSS	$2.00/M	-	-	-
236	Mistral Large 2407	Custom OSS	$2.00/M	-	-	-
237	Mistral Large 2411	Custom OSS	$2.00/M	-	-	-
238	Mixtral 8x22B Instruct	Apache 2.0	$2.00/M	141B	~$12/hr (4x A100)	HF
239	Pixtral Large 2411	Custom OSS	$2.00/M	-	-	-
240	Command A	CC BY	$2.50/M	111B	~$12/hr (4x A100)	HF
241	Llama 3.1 70B Hanami x1	Custom OSS	$3.00/M	-	-	-
242	Magnum v4 72B	Apache 2.0	$3.00/M	73B	~$4/hr (2x A100)	HF
243	Goliath 120B	Custom OSS	$3.75/M	-	-	-

Top 3 open-source LLMs

Gemma 3 12B (free) · Custom OSS · cheapest API at $0.00/M input. Self-host estimate: -.

Gemma 3 27B (free) · Custom OSS · cheapest API at $0.00/M input. Self-host estimate: -.

Gemma 3 4B (free) · Custom OSS · cheapest API at $0.00/M input. Self-host estimate: -.

Self-host vs API · when does it pay off?

Low volume

Under 1M tokens/day

Always pick API. A single GPU hour wipes out weeks of API spend at this volume.

Mid volume

10M to 100M tokens/day

Depends on model size. Small models (under 30B) are cheaper via API. Large models (200B+) favor dedicated GPUs.

High volume

1B+ tokens/day

Self-host wins, if utilization stays near 100%. Use reserved instances and bundle across workloads.

The price gap · cheapest vs most expensive

Cheapest

Gemma 3 12B (free)

$0.00/M

$ per 1M input tokens

Why the gap

Within OSS, the price range is driven by parameter count (bigger = more expensive to serve) and provider margins. Smaller dense models and heavily quantized serves sit at the bottom.

Most expensive

Goliath 120B

$3.75/M

$ per 1M input tokens

Frequently asked questions

The weights are publicly downloadable under some license (Apache 2.0, MIT, Llama Community, Qwen License, DeepSeek License, etc.). Not every "open" license is actually OSI-compliant · always read the license before commercial use.

Open source LLM pricing

Open source models · ranked by API price

Top 3 open-source LLMs

Self-host vs API · when does it pay off?

The price gap · cheapest vs most expensive

Frequently asked questions

See also

Licensing

Budget tiers

Compare