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

Reasoning Models in 2026

Updated

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

332listed
#ModelContext windowInput / 1MOutput / 1M
201Hy3 previewTencentopen weightstext262K$0.181$0.61
202Kimi K2.5MoonshotAIopen weightstext, image262K$0.451$2.251
203Kimi K2.6MoonshotAIopen weightstext, image262K$0.434$1.828
204Kimi K2.7 CodeMoonshotAIopen weightstext, image262K$0.671$3.351
205Kimi K2 ThinkingMoonshotAIopen weightstext262K$0.61$2.51
206Laguna S 2.1 (free)Poolsideopen weightstext262Kfreefree
207Laguna XS 2.1Poolsideopen weightstext262K$0.061$0.121
208Laguna XS 2.1 (free)Poolsideopen weightstext262Kfreefree
209Ling 3.0 FlashinclusionAIopen weightstext262K$0.021$0.063
210Ling 3.0 Flash FininclusionAItext262K$0.042$0.123
211Ling 3.0 Flash Sante (free)inclusionAItext262Kfreefree
212Ling 3.0 Flash VLinclusionAIopen weightstext, image, video262K$0.021$0.062
213Ling 3.1 FlashinclusionAItext262Kfreefree
214Mistral Medium 3.5Mistraltext, image, file262K$1.51$7.51
215Mistral Medium 3.5 (batch)Mistraltext, image, file262K$0.751$3.751
216Mistral Small 4Mistralopen weightstext, image262K$0.151$0.61
217Mistral Small 4 (batch)Mistralopen weightstext, image262K$0.075$0.31
218Nemotron 3.5 LightningNVIDIAopen weightstext262K$0.061$0.161
219Nemotron 3 Nano 30B A3BNVIDIAopen weightstext262K$0.051$0.21
220Nemotron 3 SuperNVIDIAopen weightstext262K$0.081$0.451
221Nemotron 3 Super (free)NVIDIAopen weightstext262Kfreefree
222Nemotron 3 UltraNVIDIAopen weightstext262K$0.51$2.21
223Nex-N2.5-MiniNex AGIopen weightstext, image262K$0.025$0.11
224Nex-N2.5-ProNex AGIopen weightstext, image262K$0.075$0.251
225Qwen3.5-122B-A10BQwenopen weightstext, image, video262K$0.261$2.081

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