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
7Hy-MT2-1.8BTencent———8K$0.077
8Nemotron 3.5 LightningNVIDIA———262K$0.085
9Solar Mini 4NEWUpstage———524K$0.087
10Ling 3.0 Flash FininclusionAI (Ant Group)———262K$0.090
11GLM 5.3 FlashbatchZ.ai (Zhipu AI) · +1 variant———1.05M$0.095
12Schematron V2 SmallNEWInference.net———128K$0.095
13GPT-6 LunaNEWbatchOpenAI · +1 variant———1.05M$0.10
14GPT-6 Luna ProNEWbatchOpenAI · +1 variant———1.05M$0.10
15Granite 4.2 8BIBM———131K$0.11
16Laguna S 2.1Poolside———1.05M$0.11
17DeepSeek V4.1 FlashNEWDeepSeek · +1 variant155.0——1.05M$0.11
18Nex-N2.5-ProNEWNex AGI———262K$0.12
19Muse Spark 1.2 ContributorMeta———1.05M$0.13
20Muse Spark 1.3 ContributorNEWMeta———1.05M$0.13
21Hy-MT2-30B-A3BTencent———8K$0.13
22Hy-MT2-7BTencent———8K$0.13
23Solar Pro 4Upstage———524K$0.16
24MiMo-V2.6-FlashNEWXiaomi———1.05M$0.17
25Ternary Bonsai 2 27BNEWPrismML———262K$0.18
26GPT-5.6 LunabatchOpenAI · +1 variant———1.05M$0.23
27GPT-5.6 Luna ProbatchOpenAI · +1 variant———1.05M$0.23
28Qwen3.8 FlashAlibaba (Qwen)———1M$0.23
29Qwen3.8 Omni FlashNEWAlibaba (Qwen)———1M$0.23
30Hy3Tencent———262K$0.23
31DeepSeek V4 Flash Vision ExpDeepSeek———1.05M$0.32
32DeepSeek V4 Flash 0731DeepSeek154.591.0—1.05M$0.33
33Gemini 3.5 Flash LitebatchGoogle · +1 variant———1.05M$0.42
34Perceptron Mk1.5NEWPerceptron———37K$0.49
35LongCat 2.0Meituan———1.05M$0.53
36MiMo-V2.6-ProNEWXiaomi———1.05M$0.54
37GLM 5.3 FlashXNEWZ.ai (Zhipu AI)———1.05M$0.59
38Inkling SmallThinking Machines Lab150.1——524K$0.64
39Muse Glimmer 30BMeta———131K$0.64
40Gemini 3.6 FlashbatchGoogle · +1 variant———1.05M$0.75
41Gemini 3.7 FlashbatchGoogle · +1 variant———1.05M$0.75
42Gemini 3.8 FlashNEWbatchGoogle · +1 variant———1.05M$0.75
43GLM 5.3batchZ.ai (Zhipu AI) · +1 variant———1.05M$0.84
44Aion 3.5 MiniNEWAionLabs———262K$0.88
45Aion-3.0-MiniAionLabs———131K$0.88
46Seed 2.1 TurboByteDance———262K$1.00
47Qwen3.8 27BAlibaba (Qwen)———1M$1.06
48Seed-2.0-CodeByteDance———262K$1.13
49Hy4 previewTencent———1.05M$1.25
50KAT-Coder-Pro V2.5Kuaishou———262K$1.29
— 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