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
4Schematron V2 TurboNEWInference.net———128K$0.060
5Hy-MT2-1.8BTencent———8K$0.077
6Nemotron 3.5 LightningNVIDIA———262K$0.085
7GLM 5.3 FlashbatchZ.ai (Zhipu AI) · +1 variant———1.05M$0.095
8Schematron V2 SmallNEWInference.net———128K$0.095
9Granite 4.2 8BIBM———131K$0.11
10Laguna S 2.1Poolside———1.05M$0.11
11DeepSeek V4.1 FlashNEWDeepSeek · +1 variant155.0——1.05M$0.11
12Nex-N2.5-ProNEWNex AGI———262K$0.12
13Hy-MT2-30B-A3BTencent———8K$0.13
14Hy-MT2-7BTencent———8K$0.13
15MiMo-V2.6-FlashNEWXiaomi———1.05M$0.17
16Ternary Bonsai 2 27BNEWPrismML———262K$0.18
17Qwen3.8 FlashAlibaba (Qwen)———1M$0.23
18Hy3Tencent———262K$0.23
19DeepSeek V4 Flash Vision ExpDeepSeek———1.05M$0.32
20DeepSeek V4 Flash 0731DeepSeek154.591.0—1.05M$0.33
21LongCat 2.0Meituan———1.05M$0.53
22MiMo-V2.6-ProNEWXiaomi———1.05M$0.54
23Inkling SmallThinking Machines Lab150.1——524K$0.64
24Muse Glimmer 30BMeta———131K$0.64
25GLM 5.3batchZ.ai (Zhipu AI) · +1 variant———1.05M$0.84
26DeepSeek V4 Pro 0813DeepSeek155.491.7—1.05M$0.99
27Qwen3.8 27BAlibaba (Qwen)———1M$1.11
28Hy4 previewTencent———1.05M$1.25
29InklingThinking Machines Lab148.6——524K$1.76
30Qwen3.8 2.4T A95BAlibaba (Qwen)———1.05M$3.00
31Kimi K3batchMoonshot AI · +1 variant———1.05M$4.56
— 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