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
1Ling 3.0 Flash VLNEWinclusionAI (Ant Group)———262K$0.031
2Ling 3.0 FlashinclusionAI (Ant Group)———262K$0.032
3Nex-N2.5-MiniNEWNex AGI———262K$0.044
4Qwen3.7 FlashAlibaba (Qwen)144.682.3—1M$0.055
5Schematron V2 TurboNEWInference.net———128K$0.060
6Mercury 2.5NEWInception Labs———260K$0.068
7Laguna XS 2.1Poolside———262K$0.075
8Hy-MT2-1.8BTencent———8K$0.077
9Nemotron 3.5 LightningNVIDIA———1M$0.085
10Solar Mini 4NEWUpstage———524K$0.087
11Ling 3.0 Flash FininclusionAI (Ant Group)———262K$0.090
12DeepSeek V4 Flash 0731DeepSeek154.591.0—1.31M$0.093
13GLM 5.3 FlashbatchZ.ai (Zhipu AI) · +1 variant———1.05M$0.095
14Schematron V2 SmallNEWInference.net———128K$0.095
15GPT-6 LunaNEWbatchOpenAI · +1 variant———1.05M$0.10
16GPT-6 Luna ProNEWbatchOpenAI · +1 variant———1.05M$0.10
17Granite 4.2 8BNEWIBM———131K$0.11
18Laguna S 2.1Poolside———1.05M$0.11
19Nex-N2.5-ProNEWNex AGI———262K$0.12
20Muse Spark 1.2 ContributorMeta———1.05M$0.13
21Muse Spark 1.3 ContributorNEWMeta———1.05M$0.13
22Hy-MT2-30B-A3BTencent———8K$0.13
23Hy-MT2-7BTencent———8K$0.13
24Solar Pro 4Upstage———524K$0.16
25DeepSeek V4.1 FlashNEWbatchDeepSeek · +1 variant———1.05M$0.17
26MiMo-V2.6-FlashNEWXiaomi———1.05M$0.17
27Ternary Bonsai 2 27BNEWPrismML———262K$0.18
28GPT-5.6 LunabatchOpenAI · +1 variant———1.05M$0.23
29GPT-5.6 Luna ProbatchOpenAI · +1 variant———1.05M$0.23
30Qwen3.8 FlashAlibaba (Qwen)———1M$0.23
31Qwen3.8 Omni FlashNEWAlibaba (Qwen)———1M$0.23
32Hy3Tencent———262K$0.23
33DeepSeek V4 Flash Vision ExpDeepSeek———1.05M$0.32
34Gemini 3.5 Flash LitebatchGoogle · +1 variant———1.05M$0.42
35Perceptron Mk1.5NEWPerceptron———37K$0.49
36LongCat 2.0Meituan———1.05M$0.53
37Muse Glimmer 30BMeta———131K$0.53
38MiMo-V2.6-ProNEWXiaomi———1.05M$0.54
39GLM 5.3 FlashXNEWZ.ai (Zhipu AI)———1.05M$0.59
40Inkling SmallThinking Machines Lab150.1——524K$0.64
41Gemini 3.6 FlashbatchGoogle · +1 variant———1.05M$0.75
42Gemini 3.7 FlashbatchGoogle · +1 variant———1.05M$0.75
43Gemini 3.8 FlashNEWbatchGoogle · +1 variant———1.05M$0.75
44GLM 5.3batchZ.ai (Zhipu AI) · +1 variant———1.05M$0.84
45Aion 3.5 MiniNEWAionLabs———262K$0.88
46Aion-3.0-MiniAionLabs———131K$0.88
47Seed 2.1 TurboByteDance———262K$1.00
48Seed-2.0-CodeByteDance———262K$1.13
49Qwen3.8 27BAlibaba (Qwen)———1M$1.15
50Hy4 previewTencent———1.05M$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