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

Longest-Context Models in 2026

Updated

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
#ModelContext windowInput / 1MOutput / 1M
251Mistral Small 4Mistralopen weightstext, image262K$0.151$0.61
252Mistral Small 4 (batch)Mistralopen weightstext, image262K$0.075$0.31
253Morph V3 LargeMorphtext262K$0.91$1.91
254Nemotron 3.5 LightningNVIDIAopen weightstext262K$0.061$0.161
255Nemotron 3 Nano 30B A3BNVIDIAopen weightstext262K$0.051$0.21
256Nemotron 3 SuperNVIDIAopen weightstext262K$0.081$0.451
257Nemotron 3 Super (free)NVIDIAopen weightstext262Kfreefree
258Nemotron 3 UltraNVIDIAopen weightstext262K$0.51$2.21
259Nex-N2.5-MiniNex AGIopen weightstext, image262K$0.025$0.11
260Nex-N2.5-ProNex AGIopen weightstext, image262K$0.075$0.251
261Paretounbiasedtext, image262K$2.51$7.51
262Qwen3 235B A22B Instruct 2507Qwenopen weightstext262K$0.088$0.351
263Qwen3 30B A3B Instruct 2507Qwenopen weightstext262K$0.048$0.193
264Qwen3.5-122B-A10BQwenopen weightstext, image, video262K$0.261$2.081
265Qwen3.5-27BQwenopen weightstext, image, video262K$0.195$1.561
266Qwen3.5-35B-A3BQwenopen weightstext, image, video262K$0.151$11
267Qwen3.5 397B A17BQwenopen weightstext, image, video262K$0.551$3.51
268Qwen3.5-9BQwenopen weightstext, image, video262K$0.11$0.151
269Qwen3.6 27BQwenopen weightstext, image, video262K$0.321$3.21
270Qwen3.6 35B A3BQwenopen weightstext, image, video262K$0.151$11
271Qwen3.6 Max PreviewQwentext262K$1.027$6.162
272Qwen3.8 27B (free)Qwenopen weightstext, image, video262Kfreefree
273Qwen3 Coder 30B A3B InstructQwenopen weightstext262K$0.071$0.281
274Qwen3 Coder 480B A35BQwenopen weightstext262K$0.31$11
275Qwen3 Coder NextQwenopen weightstext262K$0.121$0.81

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 437Open-weight models 178Vision language models 295Free models 22Newest models 466Reasoning models 332Models with tool calling 395Image generation models 9