How many open weight LLM models are available?

There are currently 94 open weight models tracked on Sector HQ. Pricing is collected every 6 hours from all major inference providers.

How is blended price calculated?

Blended price uses the formula (3 × input + 1 × output) / 4 per million tokens, reflecting typical usage where input tokens outnumber output tokens roughly 3:1.

Cheapest Open-Weight / Open Source LLM APIs in 2026

Open-weight LLMs you can self-host or access through inference providers. Compare pricing for Llama, Mistral, Qwen, and other open models.

What is the cheapest open-weight / open source LLM?

The cheapest open-weight / open source LLM API is Meta: Llama 3.2 1B Instruct via Deepinfra at $0.0063 per million tokens. 94 open weight models are compared across all providers.

Open-Weight / Open Source Models by Price

94 models

#	Model	Provider	Input	Output	Quality	Released↓
38	DeepSeek: DeepSeek V3.2 Exp Open	Deepinfra	$0.210	$0.320	Frontier	Dec 1
16	Qwen: Qwen3 Coder 30B A3B Instruct 30BOpen	Deepinfra	$0.070	$0.260	Good	Jul 14
49	Qwen: Qwen3 Coder Next Open	OpenRouter*	$0.144	$0.900	Good	Jul 14
30	Mistral: Voxtral Small 24B 2507 24BOpen	OpenRouter*	$0.120	$0.360	—	Jul 1
27	Mistral: Devstral Small 1.1 Open	OpenRouter*	$0.120	$0.360	—	May 29
14	Qwen: Qwen3 235B A22B Instruct 2507 235BOpen	OpenRouter*	$0.085	$0.120	Good	Apr 28
18	Qwen: Qwen3 14B 14BOpen	OpenRouter*	$0.072	$0.288	Good	Apr 28
19	Qwen: Qwen3 30B A3B 30BOpen	Deepinfra	$0.080	$0.280	Good	Apr 28
20	Qwen: Qwen3 32B 32BOpen	Deepinfra	$0.080	$0.280	Good	Apr 28
22	Qwen: Qwen3 30B A3B Thinking 2507 30BOpen	OpenRouter*	$0.061	$0.408	Good	Apr 28
23	Qwen: Qwen3 8B 8BOpen	OpenRouter*	$0.060	$0.480	Good	Apr 28
24	Qwen: Qwen3 30B A3B Instruct 2507 30BOpen	OpenRouter*	$0.108	$0.360	Good	Apr 28
31	Qwen: Qwen3 VL 8B Instruct 8BOpen	Novita AI	$0.080	$0.500	Good	Apr 28
35	Qwen: Qwen3 VL 32B Instruct 32BOpen	OpenRouter*	$0.125	$0.499	Good	Apr 28
43	Qwen: Qwen3 VL 30B A3B Instruct 30BOpen	Deepinfra	$0.150	$0.600	Good	Apr 28
45	Qwen: Qwen3 235B A22B 235BOpen	Deepinfra	$0.180	$0.540	Good	Apr 28
50	Qwen: Qwen3 Next 80B A3B Instruct 80BOpen	Deepinfra	$0.090	$1.10	Good	Apr 28
34	Qwen: QwQ 32B 32BOpen	Deepinfra	$0.150	$0.400	—	Mar 6
44	DeepSeek: R1 Distill Qwen 32B 32BOpen	Deepinfra	$0.270	$0.270	Frontier	Jan 20
25	NVIDIA: Llama 3.3 Nemotron Super 49B V1.5 49BOpen	Deepinfra	$0.100	$0.400	—	Dec 6
32	Meta: Llama 3.3 70B Instruct 70BOpen	OpenRouter*	$0.120	$0.384	Strong	Dec 6
42	Qwen2.5 Coder 32B Instruct 32BOpen	OpenRouter*	$0.240	$0.240	—	Nov 12
17	Mistral: Ministral 3 3B 2512 3BOpen	OpenRouter*	$0.120	$0.120	—	Oct 16
29	Mistral: Ministral 3 8B 2512 8BOpen	OpenRouter*	$0.180	$0.180	—	Oct 16
40	Mistral: Ministral 3 14B 2512 14BOpen	OpenRouter*	$0.240	$0.240	—	Oct 16
1	Meta: Llama 3.2 1B Instruct 1BOpen	Deepinfra	$0.0050	$0.010	Budget	Sep 25
2	Meta: Llama 3.2 3B Instruct 3BOpen	Deepinfra	$0.020	$0.020	Good	Sep 25
7	Meta: Llama 3.2 11B Vision Instruct 11BOpen	Deepinfra	$0.049	$0.049	Good	Sep 25
12	Qwen: Qwen2.5 7B Instruct 7BOpen	OpenRouter*	$0.048	$0.120	—	Sep 19
36	Qwen2.5 72B Instruct 72BOpen	OpenRouter*	$0.144	$0.468	—	Sep 19
39	Qwen: Qwen2.5-VL 7B Instruct 7BOpen	OpenRouter*	$0.240	$0.240	—	Sep 19
11	Mistral: Mistral Small 3 24BOpen	Deepinfra	$0.050	$0.080	—	Sep 18
15	Mistral: Mistral Small 3.2 24B 24BOpen	OpenRouter*	$0.072	$0.216	—	Sep 18
28	Mistral: Mistral Small Creative Open	OpenRouter*	$0.120	$0.360	—	Sep 18
6	Llama Guard 3 8B 8BOpen	OpenRouter*	$0.024	$0.072	—	Jul 23
26	Meta: Llama Guard 4 12B 12BOpen	Deepinfra	$0.180	$0.180	—	Jul 23
33	Meta: LlamaGuard 2 8B 8BOpen	Fireworks AI	$0.200	$0.200	—	Jul 23
3	Mistral: Mistral Nemo Open	OpenRouter*	$0.024	$0.048	—	Jul 18
13	NVIDIA: Nemotron 3 Nano 30B A3B 30BOpen	Deepinfra	$0.050	$0.200	—	Jun 14
47	NVIDIA: Nemotron Nano 12B 2 VL 12BOpen	Deepinfra	$0.200	$0.600	—	Jun 14
8	Qwen: Qwen2.5 Coder 7B Instruct 7BOpen	OpenRouter*	$0.036	$0.108	—	Jun 6
46	Qwen: Qwen2.5 VL 32B Instruct 32BOpen	Deepinfra	$0.200	$0.600	—	Jun 6
4	Meta: Llama 3 8B Instruct 8BOpen	Deepinfra	$0.030	$0.040	—	Apr 18
21	NousResearch: Hermes 2 Pro - Llama-3 8B 8BOpen	Novita AI	$0.140	$0.140	—	Jan 1
37	Nous: Hermes 4 70B 70BOpen	OpenRouter*	$0.156	$0.480	—	Jan 1
48	Nous: Hermes 3 70B Instruct 70BOpen	Deepinfra	$0.300	$0.300	Strong	Jan 1
5	Mistral: Mistral 7B Instruct v0.3 7BOpen	Deepinfra	$0.028	$0.054	Good	Sep 27
9	Mistral: Mistral 7B Instruct v0.2 7BOpen	Deepinfra	$0.055	$0.055	Good	Sep 27
10	Mistral: Mistral 7B Instruct v0.1 7BOpen	Deepinfra	$0.055	$0.055	Good	Sep 27
41	Mistral: Mistral 7B Instruct 7BOpen	OpenRouter*	$0.240	$0.240	Good	Sep 27

* Prices include ~20% OpenRouter platform fee (verified against actual billing).

All Models Frontier Chat Embedding

Frequently Asked Questions

The cheapest open-weight / open source LLM API is Meta: Llama 3.2 1B Instruct via Deepinfra at $0.0063 per million tokens (blended rate). There are 94 open weight models available.