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
4Mercury 2.5NEWInception Labs———260K$0.068
5Solar Mini 4NEWUpstage———524K$0.087
6Schematron V2 SmallNEWInference.net———128K$0.095
7GPT-6 LunaNEWbatchOpenAI · +1 variant———1.05M$0.10
8GPT-6 Luna ProNEWbatchOpenAI · +1 variant———1.05M$0.10
9Granite 4.2 8BNEWIBM———131K$0.11
10Nex-N2.5-ProNEWNex AGI———262K$0.12
11Muse Spark 1.3 ContributorNEWMeta———1.05M$0.13
12DeepSeek V4.1 FlashNEWbatchDeepSeek · +1 variant———1.05M$0.17
13MiMo-V2.6-FlashNEWXiaomi———1.05M$0.17
14Ternary Bonsai 2 27BNEWPrismML———262K$0.18
15Qwen3.8 Omni FlashNEWAlibaba (Qwen)———1M$0.23
16Perceptron Mk1.5NEWPerceptron———37K$0.49
17MiMo-V2.6-ProNEWXiaomi———1.05M$0.54
18GLM 5.3 FlashXNEWZ.ai (Zhipu AI)———1.05M$0.59
19Gemini 3.8 FlashNEWbatchGoogle · +1 variant———1.05M$0.75
20Aion 3.5 MiniNEWAionLabs———262K$0.88
21Muse Spark 1.3NEWMeta156.9——1.05M$2.00
22Claude Sonnet 5.5NEWbatchAnthropic · +1 variant———1M$2.00
23GPT-6 SolNEWbatchOpenAI · +1 variant———1.05M$2.00
24GPT-6 Sol ProNEWbatchOpenAI · +1 variant———1.05M$2.00
25Qwen3.8 Max (0902)NEWAlibaba (Qwen)155.3——1M$3.00
26Fugu MaxNEWSakana AI———1M$3.00
27Grok 4.7NEWxAI———500K$3.00
28Aion 3.5NEWAionLabs———262K$3.75
29ParetoNEWunbiased———262K$3.75
30Claude Opus 5.5NEWbatchAnthropic · +1 variant———1M$4.00
31GLM 5.3 PrimeNEWZ.ai (Zhipu AI)———1M$4.30
32MiMo-V2.6-Pro-UltraSpeedNEWXiaomi———1.05M$5.44
33Ember-1NEWFireworks AI———1.05M$6.00
34Qwen3.8 Max PrimeNEWAlibaba (Qwen)———1M$6.00
35Claude Fable 5.1NEWbatchAnthropic · +1 variant———1M$10.00
36GPT-6 AstraNEWbatchOpenAI · +1 variant———1.05M$10.00
37GPT-6 Astra ProNEWbatchOpenAI · +1 variant———1.05M$10.00
38Fugu Ultra v2NEWSakana AI———1M$11.25
— 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