Cheapest Language Models in 2026

Updated 7 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
26	Gemini 2.5 Flash Lite (batch)Googletext, image, file, audio, video	1M	$0.051	$0.21
27	Gemma 3 12BGoogleopen weightstext, image	131K	$0.051	$0.151
28	Gemma 3 4BGoogleopen weightstext, image	131K	$0.051	$0.11
29	GPT-4.1 Nano (batch)OpenAIimage, text, file	1M	$0.051	$0.21
30	GPT-5 NanoOpenAItext, image, file	400K	$0.051	$0.41
31	GPT-6 Luna (batch)OpenAIfile, image, text	1.1M	$0.051	$0.251
32	GPT-6 Luna Pro (batch)OpenAIfile, image, text	1.1M	$0.051	$0.251
33	Llama 3.1 8B InstructMetaopen weightstext	131K	$0.051	$0.081
34	Llama 3.2 3B InstructMetaopen weightstext	131K	$0.051	$0.331
35	Mistral Small 3Mistralopen weightstext	33K	$0.051	$0.081
36	Nemotron 3 Nano 30B A3BNVIDIAopen weightstext	262K	$0.051	$0.21
37	Schematron V2 SmallInference.netopen weightstext	128K	$0.051	$0.231
38	Solar Mini 4Upstagetext	524K	$0.051	$0.21
39	GLM 5.3 Flash (batch)Z.aiopen weightstext, image, video	1M	$0.061	$0.21
40	Granite 4.2 8BIBMopen weightstext	131K	$0.061	$0.251
41	Laguna XS 2.1Poolsideopen weightstext	262K	$0.061	$0.121
42	Nemotron 3.5 LightningNVIDIAopen weightstext	262K	$0.061	$0.161
43	Nova Lite 1.0Amazontext, image	300K	$0.061	$0.241
44	GLM 4.7 FlashZ.aiopen weightstext	200K	$0.061	$0.41
45	Qwen3.5-FlashQwentext, image, video	1M	$0.065	$0.261
46	Gemma 4 26B A4B Googleopen weightsimage, text, video	262K	$0.068	$0.225
47	Phi 4Microsoftopen weightstext	16K	$0.071	$0.141
48	Qwen3 Coder 30B A3B InstructQwenopen weightstext	262K	$0.071	$0.281
49	Hy-MT2-30B-A3BTencentopen weightstext	8K	$0.074	$0.295
50	Hy-MT2-7BTencentopen weightstext	8K	$0.074	$0.295

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