Cheapest Language Models in 2026

Updated 8 October 2026

437 on record. Sorted by input price; every figure comes from the OpenRouter model catalogue, with the page it was read from on each entry.

437listed

#	Model	Context window	Input / 1M	Output / 1M
126	Llama 4 MaverickMetaopen weightstext, image	1M	$0.188	$0.653
127	Qwen3.6 FlashQwentext, image, video	1M	$0.188	$1.125
128	Qwen3.5-27BQwenopen weightstext, image, video	262K	$0.195	$1.561
129	Qwen3 Coder FlashQwentext	1M	$0.195	$0.975
130	GPT-4.1 Mini (batch)OpenAIimage, text, file	1M	$0.21	$0.81
131	GPT-5.4 NanoOpenAIfile, image, text	400K	$0.21	$1.251
132	GPT-5.6 LunaOpenAIfile, image, text	1.1M	$0.21	$1.21
133	GPT-5.6 Luna ProOpenAIfile, image, text	1.1M	$0.21	$1.21
134	MiniMax-01MiniMaxopen weightstext, image	1M	$0.21	$1.11
135	Ministral 3 14B 2512Mistralopen weightstext, image	262K	$0.21	$0.21
136	Mistral Medium 3.1 (batch)Mistraltext, image, file	131K	$0.21	$11
137	Nemotron 3.5 Content SafetyNVIDIAopen weightstext, image	131K	$0.21	$0.21
138	Qwen3 30B A3B Thinking 2507Qwenopen weightstext	82K	$0.21	$2.41
139	Qwen3 VL 30B A3B ThinkingQwenopen weightstext, image	262K	$0.21	$2.41
140	SabaMistraltext, file	33K	$0.21	$0.61
141	Step 3.7 FlashStepFunopen weightstext, image, video	262K	$0.21	$1.151
142	UncensoredVeniceopen weightstext	128K	$0.21	$0.91
143	DeepSeek V4 Pro 0423DeepSeekopen weightstext	1M	$0.209	$0.418
144	MiniMax M2.7MiniMaxopen weightstext	205K	$0.211	$0.841
145	Qwen3 VL 235B A22B InstructQwenopen weightstext, image	262K	$0.211	$1.91
146	DeepSeek V4 Flash Vision ExpDeepSeekopen weightstext, image	1M	$0.216	$0.647
147	Qwen3 235B A22B Thinking 2507Qwenopen weightstext	131K	$0.231	$2.31
148	DeepSeek V3.1DeepSeekopen weightstext	164K	$0.251	$0.951
149	Gemini 3.1 Flash LiteGoogletext, image, video, file, audio	1M	$0.251	$1.51
150	Gemini 3.1 Flash Lite PreviewGoogletext, image, video, file, audio	1M	$0.251	$1.51

Context bars share one log scale, 1K to 2M tokens. Prices are what each provider publishes per million tokens; 'varies' is a router that bills the model it picks.

More in Models

All models lists

Longest-context models 466 Open-weight models 178 Vision language models 295 Free models 22 Newest models 466 Reasoning models 332 Models with tool calling 395 Image generation models 9