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
76	Llama 3.3 70B InstructMetaopen weightstext	131K	$0.11	$0.321
77	Llama 4 ScoutMetaopen weightstext, image	1.3M	$0.11	$0.31
78	Ministral 3 3B 2512Mistralopen weightstext, image	131K	$0.11	$0.11
79	Muse Spark 1.2 ContributorMetatext, image, video, file	1M	$0.11	$0.21
80	Muse Spark 1.3 ContributorMetatext, image, video, file	1M	$0.11	$0.21
81	Qwen2.5 7B InstructQwenopen weightstext	33K	$0.11	$0.21
82	Qwen3.5-9BQwenopen weightstext, image, video	262K	$0.11	$0.151
83	Qwen3 Next 80B A3B InstructQwenopen weightstext	262K	$0.11	$1.11
84	Reka Edgerekaaiopen weightsimage, text, video	16K	$0.11	$0.11
85	Reka Flash 3rekaaiopen weightstext	66K	$0.11	$0.21
86	Seed-2.0-MiniByteDance Seedtext, image, video	262K	$0.11	$0.41
87	Step 3.5 FlashStepFunopen weightstext	262K	$0.11	$0.31
88	UI-TARS 7B ByteDanceopen weightsimage, text	128K	$0.11	$0.21
89	Voxtral Small 24B 2507Mistralopen weightstext, audio, file	33K	$0.11	$0.31
90	Qwen3 VL 32B InstructQwenopen weightstext, image	131K	$0.104	$0.416
91	DeepSeek V4.1 Flash (batch)DeepSeekopen weightstext, image	1M	$0.112	$0.336
92	Qwen3 8BQwenopen weightstext	131K	$0.117	$0.455
93	Qwen3 VL 8B InstructQwenopen weightsimage, text	262K	$0.117	$0.455
94	GLM LatestZ.aitext	1M	$0.121	$41
95	Qwen3 14BQwenopen weightstext	131K	$0.121	$0.241
96	Qwen3 30B A3BQwenopen weightstext	131K	$0.121	$0.51
97	Qwen3 Coder NextQwenopen weightstext	262K	$0.121	$0.81
98	Gemini 3.1 Flash Lite (batch)Googletext, image, video, file, audio	1M	$0.125	$0.751
99	GPT-5 Mini (batch)OpenAItext, image, file	400K	$0.125	$11
100	GLM 4.5 AirZ.aiopen weightstext	131K	$0.131	$0.851

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