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
151MiMo-V2.6-ProNEWXiaomi———1.05M$0.54
152Qwen3.7 PlusAlibaba (Qwen)147.487.9—1M$0.56
153Gemini 3 Flash PreviewbatchGoogle · +1 variant———1.05M$0.56
154Gemini 3.1 Flash Lite PreviewGoogle———1.05M$0.56
155Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google———66K$0.56
156Qwen3.5 Plus 2026-02-15Alibaba (Qwen)—84.8—1M$0.58
157GLM 5.3 FlashXNEWZ.ai (Zhipu AI)———1.05M$0.59
158Skyfall 36B V2TheDrummer———33K$0.61
159WizardLM-2 8x22BMicrosoft—43.4—66K$0.62
160ERNIE 4.5 VL 424B A47BBaidu———123K$0.63
161Qwen3 VL 235B A22B InstructAlibaba (Qwen)———262K$0.63
162Inkling SmallThinking Machines Lab150.1——524K$0.64
163Gemma 2 27BGoogle122.136.5—8K$0.65
164Qwen3 VL 8B ThinkingAlibaba (Qwen)———131K$0.66
165Llama 3.3 Euryale 70BSao10K———131K$0.68
166GPT-5.1-Codex-MiniOpenAI———400K$0.69
167Seed 1.6ByteDance———262K$0.69
168Seed-2.0-LiteByteDance———262K$0.69
169Hermes 3 70B InstructNous Research———131K$0.70
170Qwen3.5-122B-A10BAlibaba (Qwen)———262K$0.71
171Qwen3.6 PlusAlibaba (Qwen)———1M$0.73
172Qwen2.5 Coder 32B InstructAlibaba (Qwen)———33K$0.74
173Qwen3 235B A22B Thinking 2507Alibaba (Qwen)———131K$0.75
174Gemini 3.6 FlashbatchGoogle · +1 variant———1.05M$0.75
175Gemini 3.7 FlashbatchGoogle · +1 variant———1.05M$0.75
176Gemini 3.8 FlashNEWbatchGoogle · +1 variant———1.05M$0.75
177Qwen3 30B A3B Thinking 2507Alibaba (Qwen)———82K$0.75
178Qwen3 VL 30B A3B ThinkingAlibaba (Qwen)———262K$0.75
179GLM 4.6Z.ai (Zhipu AI)———205K$0.76
180Qwen3 235B A22BAlibaba (Qwen)139.470.7—131K$0.80
181Mistral Medium 3Mistral AI134.159.5—131K$0.80
182Devstral 2 2512Mistral AI———262K$0.80
183GLM 5.3batchZ.ai (Zhipu AI) · +1 variant———1.05M$0.84
184GPT-5.4 MinibatchOpenAI · +1 variant———400K$0.84
185Llama 3.1 Euryale 70B v2.2Sao10K———131K$0.85
186MiniMax M1MiniMax———1M$0.85
187Nano Banana (Gemini 2.5 Flash Image)Google———33K$0.85
188Nova 2 LiteAmazon———1M$0.85
189Qwen2.5 VL 72B InstructAlibaba (Qwen)———128K$0.85
190Aion 3.5 MiniNEWAionLabs———262K$0.88
191Aion-3.0-MiniAionLabs———131K$0.88
192Kimi K2.5Moonshot AI148.1——262K$0.90
193GLM 4.5VZ.ai (Zhipu AI)———66K$0.90
194Morph V3 FastMorph———82K$0.90
195R1 0528DeepSeek———164K$0.91
196GLM 5Z.ai (Zhipu AI)145.887.8—205K$0.93
197Relace Apply 3Relace———256K$0.95
198o3 MinibatchOpenAI · +1 variant———200K$0.96
199o4 MinibatchOpenAI · +1 variant———200K$0.96
200GLM 4.7Z.ai (Zhipu AI)143.583.3—205K$1.00
— 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