Skip to content

Longest context

Ranked by maximum context window (tokens) as listed by the API provider.

Ranked by maximum context window (tokens) as listed by the API provider. Source: OpenRouter. Variants (reasoning effort, batch) are folded into one row.

#ModelCapabilityReasoningCodingContext$/M
151Hy3 previewTencent———262K$0.28
152KAT-Coder-Pro V2.5Kuaishou———262K$1.29
153Kimi K2 0905Moonshot AI———262K$1.07
154Laguna XS 2.1Poolside———262K$0.075
155Ling 3.0 FlashinclusionAI (Ant Group)———262K$0.032
156Ling 3.0 Flash FininclusionAI (Ant Group)———262K$0.090
157Ling 3.0 Flash VLNEWinclusionAI (Ant Group)———262K$0.031
158Ministral 3 14B 2512Mistral AI———262K$0.20
159Ministral 3 8B 2512Mistral AI · +1 variant———262K$0.15
160Mistral Large 3 2512Mistral AI · +1 variant———262K$0.75
161Mistral Medium 3.5batchMistral AI · +1 variant———262K$1.50
162Mistral Small 4Mistral AI · +1 variant———262K$0.26
163Morph V3 LargeMorph———262K$1.15
164Nemotron 3 Nano 30B A3BNVIDIA———262K$0.087
165Nemotron 3 SuperNVIDIA———262K$0.17
166Nemotron 3.5 LightningNVIDIA———262K$0.085
167Nex-N2.5-MiniNEWNex AGI———262K$0.044
168Nex-N2.5-ProNEWNex AGI———262K$0.12
169ParetoNEWunbiased———262K$3.75
170Qwen3 235B A22B Instruct 2507Alibaba (Qwen)———262K$0.15
171Qwen3 30B A3B Instruct 2507Alibaba (Qwen)———262K$0.084
172Qwen3 Coder 30B A3B InstructAlibaba (Qwen)———262K$0.12
173Qwen3 Coder 480B A35BAlibaba (Qwen)———262K$0.47
174Qwen3 Coder NextAlibaba (Qwen)———262K$0.29
175Qwen3 Max ThinkingAlibaba (Qwen)———262K$1.56
176Qwen3 Next 80B A3B InstructAlibaba (Qwen)———262K$0.35
177Qwen3 Next 80B A3B ThinkingAlibaba (Qwen)———262K$0.41
178Qwen3 VL 235B A22B InstructAlibaba (Qwen)———262K$0.63
179Qwen3 VL 30B A3B InstructAlibaba (Qwen)———262K$0.26
180Qwen3 VL 30B A3B ThinkingAlibaba (Qwen)———262K$0.75
181Qwen3 VL 8B InstructAlibaba (Qwen)———262K$0.20
182Qwen3.5-122B-A10BAlibaba (Qwen)———262K$0.71
183Qwen3.5-27BAlibaba (Qwen)———262K$0.54
184Qwen3.6 35B A3BAlibaba (Qwen)—84.8—262K$0.36
185Qwen3.6 Max PreviewAlibaba (Qwen)———262K$2.31
186Sakana NamazuSakana AI———262K$1.71
187Seed 1.6ByteDance———262K$0.69
188Seed 1.6 FlashByteDance———262K$0.13
189Seed 2.1 TurboByteDance———262K$1.00
190Seed-2.0-CodeByteDance———262K$1.13
191Seed-2.0-LiteByteDance———262K$0.69
192Seed-2.0-MiniByteDance———262K$0.17
193Step 3.5 FlashStepFun———262K$0.15
194Step 3.7 FlashStepFun———262K$0.44
195Ternary Bonsai 2 27BNEWPrismML———262K$0.18
196Trinity Large ThinkingArcee AI———262K$0.39
197Mercury 2.5NEWInception Labs———260K$0.068
198Codestral 2508Mistral AI · +1 variant———256K$0.45
199Command ACohere———256K$4.38
200Grok Build 0.1xAI———256K$1.25
— means no published score from that source yet · click a model for every benchmark with its source

New - awaiting independent evaluation

All new models →

Not ranked until an independent evaluator (Epoch AI) publishes scores. We don't use vendor-reported benchmark claims for rankings.

Best AI for coding →
Models ranked on DeepSWE
Best AI for reasoning →
Ranked on GPQA Diamond
Best AI for math →
Ranked on competition math
Best open-weight models →
Weights you can run yourself
Cheapest capable models →
Lowest blended API price
Best AI coding tools →
Apps & agents by popularity
Best AI image generators →
Apps & models
Best AI for research →
Answer engines & deep research