What is blended price per million tokens?

Blended price is calculated as (3 × input price + 1 × output price) / 4 per million tokens. This approximates typical LLM usage where input tokens outnumber output tokens roughly 3:1.

How often are LLM prices updated?

Sector HQ collects pricing data every 6 hours from all major providers including OpenRouter, DeepInfra, Together AI, and direct APIs. Price alerts are generated when significant changes are detected.

Cheapest LLM APIs in 2026 — Ranked by Price Per Token

Every LLM API ranked by blended price per million tokens. Find the lowest-cost model for your use case across 200+ options.

What is the cheapest LLM API right now?

The cheapest LLM API is Japanese Stable Diffusion XL via Fireworks AI at $0.0001 per million tokens (blended rate). This ranking covers 200+ models across 23 providers, updated every 6 hours.

Open WeightModels you can self-host FrontierTop-tier quality models ChatConversational models EmbeddingText embedding models

All Models by Price

200 models

#	Model	Provider	Input	Output	Quality	Released↓
183	Nova 2 Multimodal Embeddings	AWS Bedrock	$0.135	Free	—	Dec 2
193	Allenai Olmocr 2 7B 1025	Deepinfra	$0.090	$0.190	—	Oct 25
194	Qwen: Qwen3 Coder 30B A3B Instruct 30BOpen	Deepinfra	$0.070	$0.260	Good	Jul 14
67	Voxtral Mini 3B 2507	AWS Bedrock	$0.040	$0.040	—	Jul 1
49	Paddlepaddle Paddleocr VL	Novita AI	$0.020	$0.020	—	Jun 30
198	Baidu: ERNIE 4.5 21B A3B 21B	Novita AI	$0.070	$0.280	—	Jun 30
199	Baidu: ERNIE 4.5 21B A3B Thinking 21B	Novita AI	$0.070	$0.280	—	Jun 30
98	Baichuan Baichuan M2 32B	Novita AI	$0.070	$0.070	—	Jun 1
164	Minimax M1 80K	Fireworks AI	$0.100	$0.100	—	Jun 1
95	DeepSeek R1 0528 Qwen3 8B	Novita AI	$0.060	$0.090	Frontier	May 28
82	OpenAI: gpt-oss-20b 20B	Deepinfra	$0.030	$0.140	—	May 1
115	OpenAI: gpt-oss-120b 120B	Deepinfra	$0.039	$0.190	—	May 1
130	OpenAI: gpt-oss-120b (exacto) 120B	OpenRouter*	$0.047	$0.228	—	May 1
184	OpenAI: gpt-oss-safeguard-20b 20B	AWS Bedrock	$0.070	$0.200	—	May 1
13	Qwen3 Embedding 0 6B Batch	Deepinfra	$0.0050	Free	Good	Apr 28
30	Qwen3 Reranker 0 6B	Deepinfra	$0.010	Free	Good	Apr 28
33	Qwen3 Embedding 4B Batch	Deepinfra	$0.010	Free	Good	Apr 28
36	Qwen3 Embedding 8B	Deepinfra	$0.010	Free	Good	Apr 28
38	Qwen3 Embedding 0 6B	Deepinfra	$0.010	Free	Good	Apr 28
44	Qwen3 Embedding 4B	Deepinfra	$0.020	Free	Good	Apr 28
46	Qwen3 Reranker 4B	Deepinfra	$0.025	Free	Good	Apr 28
58	Qwen3 4B Fp8	Novita AI	$0.030	$0.030	Good	Apr 28
59	Qwen3 Embedding 8B Batch	Deepinfra	$0.040	Free	Good	Apr 28
63	Qwen3 Reranker 8B	Deepinfra	$0.050	Free	Good	Apr 28
88	Qwen3 8B Fp8	Novita AI	$0.035	$0.138	Good	Apr 28
116	Qwen3 235B A22b Instruct 2507	Deepinfra	$0.071	$0.100	Good	Apr 28
126	qwen-turbo	Alibaba Cloud	$0.050	$0.200	—	Apr 28
131	Qwen: Qwen3 235B A22B Instruct 2507 235BOpen	OpenRouter*	$0.085	$0.120	Good	Apr 28
141	Qwen3 1.7b Fp8 Draft	Fireworks AI	$0.100	$0.100	Good	Apr 28
144	Qwen3 1.7b	Fireworks AI	$0.100	$0.100	Good	Apr 28
159	Qwen3 1.7b Fp8 Draft 40960	Fireworks AI	$0.100	$0.100	Good	Apr 28
161	Qwen3 1.7b Fp8 Draft 131072	Fireworks AI	$0.100	$0.100	Good	Apr 28
170	Qwen3 0.6b	Fireworks AI	$0.100	$0.100	Good	Apr 28
129	Embed V 4.0	Azure OpenAI	$0.120	Free	—	Apr 15
147	Cogito V1 Preview Llama 3B	Fireworks AI	$0.100	$0.100	—	Apr 1
185	AllenAI: Olmo 2 32B Instruct 32B	OpenRouter*	$0.060	$0.240	—	Mar 25
190	Gemini Embedding 001	Google	$0.150	Free	—	Mar 25
54	Google: Gemma 3n 4B 4B	Together AI	$0.020	$0.040	—	Mar 12
72	Google: Gemma 3 4B 4B	AWS Bedrock	$0.040	$0.080	—	Mar 12
92	Google: Gemma 3 12B 12B	Deepinfra	$0.040	$0.130	—	Mar 12
155	Google: Gemma 3 27B 27B	Deepinfra	$0.080	$0.160	—	Mar 12
120	Gte Modernbert Base	Together AI	$0.080	$0.080	—	Mar 1
93	Phi 4 Multimodal Instruct	Deepinfra	$0.050	$0.100	—	Feb 26
117	Command R7b 12 2024 7B	OpenRouter*	$0.045	$0.180	—	Feb 3
57	DeepSeek Ocr	Novita AI	$0.030	$0.030	—	Jan 20
146	DeepSeek R1 Distill Qwen 1.5b	Fireworks AI	$0.100	$0.100	Frontier	Jan 20
89	Zai Org Autoglm Phone 9B Multilingual	Novita AI	$0.035	$0.138	—	Jan 7
123	Microsoft: Phi 4	Deepinfra	$0.070	$0.140	—	Dec 12
90	Nova Micro	AWS Bedrock	$0.035	$0.140	—	Dec 4
91	Nova Micro V1	AWS Bedrock	$0.035	$0.140	—	Dec 4

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

Frequently Asked Questions

The cheapest LLM API is Japanese Stable Diffusion XL via Fireworks AI at $0.0001 per million tokens. Prices are compared using a blended rate (3:1 input-to-output ratio) across 200+ models.