Longest-Context Models in 2026

Updated 7 October 2026

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

466listed

#	Model	Context window	Input / 1M	Output / 1M
426	Morph V3 FastMorphtext	82K	$0.81	$1.21
427	Qwen3 30B A3B Thinking 2507Qwenopen weightstext	82K	$0.21	$2.41
428	GLM 4.5VZ.aiopen weightstext, image	66K	$0.61	$1.81
429	LFM2.5-2.6B (free)LiquidAIopen weightstext	66K	free	free
430	MiniMax M2-herMiniMaxtext	66K	$0.31	$1.21
431	Mixtral 8x22B InstructMistralopen weightstext, file	66K	$21	$61
432	Nano Banana 2 (Gemini 3.1 Flash Image Preview)Googleimage, text	66K	$0.51	$31
433	Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Googleimage, text	66K	$0.251	$1.51
434	Nano Banana Pro (Gemini 3 Pro Image Preview)Googleimage, text	66K	$21	$121
435	Reka Flash 3rekaaiopen weightstext	66K	$0.11	$0.21
436	WizardLM-2 8x22Bmicrosoftopen weightstext	66K	$0.621	$0.621
437	R1DeepSeekopen weightstext	64K	$0.71	$2.51
438	Llama 3.2 1B InstructMetaopen weightstext	60K	$0.027	$0.201
439	Perceptron Mk1.5Perceptrontext, image, video, audio	37K	$0.151	$1.51
440	Aion-RP 1.0 (8B)AionLabstext	33K	$0.81	$1.61
441	Magnum v4 72Banthracite-orgopen weightstext	33K	$2.51	$51
442	Mistral Small 3Mistralopen weightstext	33K	$0.051	$0.081
443	Nano Banana (Gemini 2.5 Flash Image)Googleimage, text	33K	$0.31	$2.51
444	Perceptron Mk1Perceptrontext, image, video	33K	$0.151	$1.51
445	Qwen2.5 72B Instructqwenopen weightstext	33K	$0.361	$0.41
446	Qwen2.5 7B InstructQwenopen weightstext	33K	$0.11	$0.21
447	Qwen2.5 Coder 32B Instructqwenopen weightstext	33K	$0.661	$11
448	SabaMistraltext, file	33K	$0.21	$0.61
449	Skyfall 36B V2TheDrummeropen weightstext	33K	$0.551	$0.81
450	Voxtral Small 24B 2507Mistralopen weightstext, audio, file	33K	$0.11	$0.31

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

Cheapest language models 437 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