Skip to content

Cheapest models

Ranked by blended API price (75% input + 25% output, USD per 1M tokens). Free promotional listings excluded.

Ranked by blended API price (75% input + 25% output, USD per 1M tokens). Free promotional listings excluded. Source: OpenRouter. Variants (reasoning effort, batch) are folded into one row.

#ModelCapabilityReasoningCodingContext$/M
51Llama 3.3 70B InstructMeta———131K$0.15
52DeepSeek V4.1 FlashNEWbatchDeepSeek · +1 variant———1.05M$0.17
53Gemma 3 27BGoogle130.047.7—131K$0.17
54Nemotron 3 SuperNVIDIA———262K$0.17
55DeepSeek V4 Flash 0423DeepSeek146.1——1.05M$0.17
56MiMo-V2.5Xiaomi———1.05M$0.17
57MiMo-V2.6-FlashNEWXiaomi———1.05M$0.17
58Llama Guard 4 12BMeta———164K$0.18
59Ternary Bonsai 2 27BNEWPrismML———262K$0.18
60Qwen3 VL 32B InstructAlibaba (Qwen)———131K$0.18
61Ministral 3 14B 2512Mistral AI———262K$0.20
62Nemotron 3.5 Content SafetyNVIDIA———131K$0.20
63Qwen3 8BAlibaba (Qwen)136.256.8—131K$0.20
64Qwen3 VL 8B InstructAlibaba (Qwen)———262K$0.20
65Qwen3 30B A3BAlibaba (Qwen)136.261.7—131K$0.23
66Qwen3.8 FlashAlibaba (Qwen)———1M$0.23
67Hy3Tencent———262K$0.23
68Hunyuan A13B InstructTencent———131K$0.25
69Qwen3 VL 30B A3B InstructAlibaba (Qwen)———262K$0.26
70Hy3 previewTencent———262K$0.28
71Qwen3 Coder NextAlibaba (Qwen)———262K$0.29
72Llama 4 MaverickMeta132.2——1.05M$0.30
73DeepSeek V3.2 ExpDeepSeek145.0——164K$0.30
74GLM 4.5 AirZ.ai (Zhipu AI)———131K$0.31
75DeepSeek V3.2DeepSeek146.383.4—164K$0.32
76DeepSeek V4 Flash Vision ExpDeepSeek———1.05M$0.32
77Cydonia 24B V4.1TheDrummer———131K$0.35
78Qwen3 Next 80B A3B InstructAlibaba (Qwen)———262K$0.35
79Qwen3.6 35B A3BAlibaba (Qwen)—84.8—262K$0.36
80MiniMax M2.7MiniMax145.8——205K$0.37
81Qwen2.5 72B InstructAlibaba (Qwen)———33K$0.37
82UncensoredVenice———128K$0.38
83Trinity Large ThinkingArcee AI———262K$0.39
84Llama 3.1 70B InstructMeta———131K$0.40
85UnslopNemo 12BTheDrummer———1.02M$0.40
86Mistral Small 3.1 24BMistral AI———128K$0.40
87Qwen3 Next 80B A3B ThinkingAlibaba (Qwen)———262K$0.41
88DeepSeek V3.1DeepSeek139.9——164K$0.42
89MiniMax-01MiniMax———1M$0.42
90ReMM SLERP 13Bundi95———6K$0.42
91Step 3.7 FlashStepFun———262K$0.44
92Qwen3.5-35B-A3BAlibaba (Qwen)142.583.5—262K$0.45
93GLM 4.6VZ.ai (Zhipu AI)———131K$0.45
94DeepSeek V3DeepSeek132.456.5—164K$0.45
95MiniMax M2.5MiniMax146.7——205K$0.47
96DeepSeek V3.1 TerminusDeepSeek———164K$0.47
97Qwen3 Coder 480B A35BAlibaba (Qwen)———262K$0.47
98DeepSeek V3 0324DeepSeek———164K$0.50
99MiniMax M3MiniMax147.090.9—1.05M$0.53
100LongCat 2.0Meituan———1.05M$0.53
— 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