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
2Nex-N2.5-MiniNEWNex AGI———262K$0.044
3Schematron V2 TurboNEWInference.net———128K$0.060
4Schematron V2 SmallNEWInference.net———128K$0.095
5Granite 4.2 8BNEWIBM———131K$0.11
6Nex-N2.5-ProNEWNex AGI———262K$0.12
7DeepSeek V4.1 FlashNEWbatchDeepSeek · +1 variant———1.05M$0.17
8MiMo-V2.6-FlashNEWXiaomi———1.05M$0.17
9Ternary Bonsai 2 27BNEWPrismML———262K$0.18
10MiMo-V2.6-ProNEWXiaomi———1.05M$0.54
— 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