Inferse
For vendors
AdvertiseTop spots, featured rows, home sponsor Get listedAdd a product we don't cover yet Claim a listingFree: verify the domain, then correct your page Vendor dashboardNumbers, orders and placements
List your platform
Vendor dashboard

Open-Weight Models in 2026

Updated

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

178listed
#ModelContext windowInput / 1MOutput / 1M
26MiniMax M3MiniMaxopen weightstext, image, video1M$0.31$1.21
27Qwen3.8 2.4T A95BQwenopen weightstext1M$21$61
28UnslopNemo 12BTheDrummeropen weightstext1M$0.41$0.41
29MiniMax-01MiniMaxopen weightstext, image1M$0.21$1.11
30Nemotron 3.5 Lightning (free)NVIDIAopen weightstext1Mfreefree
31Nemotron 3 Ultra (free)NVIDIAopen weightstext1Mfreefree
32Qwen3.8 27BQwenopen weightstext, image, video1M$0.421$31
33Qwen3.8 FlashQwenopen weightstext, image, video1M$0.151$0.471
34InklingThinking Machinesopen weightstext, image, audio524K$0.951$4.051
35Inkling SmallThinking Machinesopen weightstext, image, audio524K$0.451$1.21
36Devstral 2 2512Mistralopen weightstext, file262K$0.41$21
37Gemma 4 26B A4B Googleopen weightsimage, text, video262K$0.068$0.225
38Gemma 4 26B A4B (free)Googleopen weightsimage, text, video262Kfreefree
39Gemma 4 31BGoogleopen weightsimage, text, video262K$0.091$0.341
40Gemma 4 31B (free)Googleopen weightsimage, text, video262Kfreefree
41Hy3Tencentopen weightstext262K$0.083$0.331
42Hy3 previewTencentopen weightstext262K$0.181$0.61
43Kimi K2 0905MoonshotAIopen weightstext262K$0.61$2.51
44Kimi K2.5MoonshotAIopen weightstext, image262K$0.451$2.251
45Kimi K2.6MoonshotAIopen weightstext, image262K$0.434$1.828
46Kimi K2.7 CodeMoonshotAIopen weightstext, image262K$0.671$3.351
47Kimi K2 ThinkingMoonshotAIopen weightstext262K$0.61$2.51
48Laguna S 2.1 (free)Poolsideopen weightstext262Kfreefree
49Laguna XS 2.1Poolsideopen weightstext262K$0.061$0.121
50Laguna XS 2.1 (free)Poolsideopen weightstext262Kfreefree

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 437Longest-context models 466Vision language models 295Free models 22Newest models 466Reasoning models 332Models with tool calling 395Image generation models 9