What 1M LLM tokens costs

Price per million tokens for 359 models, cheapest first. "1M tokens" here is 75% input and 25% output, a typical chat or agent mix; input and output are shown separately too. Prices are OpenRouter's, which pass through each provider's list price for most models. Checked twice a day.

ModelMaker1M tokensInput /1MOutput /1MContext7-day change
Ling 3.0 Tinyinclusionai$0.022$0.015$0.045 262k
Mistral Nemomistralai$0.029$0.029$0.030 131k
Extractscaledown$0.030$0.040$0.00 1,000k
Summarizescaledown$0.030$0.040$0.00 1,000k
Ling 3.0 Flashinclusionai$0.032$0.021$0.063 262k
Llama 3 8B Lunarissao10k$0.042$0.040$0.050 8k
Nex-N2.5-Mininex-agi$0.044$0.025$0.10 262k
GLM Flash Latest~z-ai$0.044$0.029$0.092 1,048k
gpt-oss-20bopenai$0.055$0.030$0.13 131k
Qwen3.7 Flashqwen$0.055$0.030$0.13 1,000k
Llama 3.1 8B Instructmeta-llama$0.058$0.050$0.080 131k
Mistral Small 3mistralai$0.058$0.050$0.080 32k
Schematron V2 Turboinference-net$0.060$0.030$0.15 128k
Nova Micro 1.0amazon$0.061$0.035$0.14 128k
Gemma 3 4Bgoogle$0.062$0.050$0.10 131k
Command R7B (12-2024)cohere$0.066$0.037$0.15 128k
Mercury 2.5inception$0.068$0.040$0.15 260k
Llama 3.2 1B Instructmeta-llama$0.071$0.027$0.20 60k
Gemma 3 12Bgoogle$0.075$0.050$0.15 131k
Hy-MT2-1.8Btencent$0.077$0.044$0.18 8k
MythoMax 13Bgryphe$0.087$0.080$0.11 8k
Phi 4microsoft$0.088$0.070$0.14 16k
Solar Mini 4upstage$0.088$0.050$0.20 524k
Ling 3.0 Flash VLinclusionai$0.090$0.060$0.18 131k
Ternary Bonsai 2 9Bprism-ml$0.092$0.080$0.13 262k
Schematron V2 Smallinference-net$0.095$0.050$0.23 128k
Ministral 3 3B 2512mistralai$0.10$0.10$0.10 131k
Reka Edgerekaai$0.10$0.10$0.10 16k
Nemotron 3.5 Lightningnvidia$0.10$0.070$0.20 262k
Nova Lite 1.0amazon$0.10$0.060$0.24 300k
Nemotron 3 Nano 30B A3Bnvidia$0.10$0.060$0.24 262k
Mistral Small 3.2 24Bmistralai$0.11$0.075$0.20 256k
Gemma 4 26B A4B google$0.11$0.071$0.21 262k
Granite 4.2 8Bibm-granite$0.11$0.060$0.25 131k
Ling 3.1 Flashinclusionai$0.11$0.075$0.23 1,000k
DeepSeek V4 Flash 0423deepseek$0.11$0.091$0.18 1,048k
Qwen3.5-Flashqwen$0.11$0.065$0.26 1,000k
Nex-N2.5-Pronex-agi$0.12$0.075$0.25 262k
DeepSeek V4 Flash 0731deepseek$0.12$0.059$0.30 1,048k
DeepSeek V4 Flash Latest~deepseek$0.12$0.059$0.30 1,048k
Llama 3.2 3B Instructmeta-llama$0.12$0.051$0.34 131k
UI-TARS 7B bytedance$0.12$0.10$0.20 128k
Muse Spark 1.2 Contributormeta$0.12$0.10$0.20 1,048k
Muse Spark 1.3 Contributormeta$0.12$0.10$0.20 1,048k
Qwen2.5 7B Instructqwen$0.12$0.10$0.20 32k
Reka Flash 3rekaai$0.12$0.10$0.20 65k
Hy-MT2-30B-A3Btencent$0.13$0.074$0.29 8k
Hy-MT2-7Btencent$0.13$0.074$0.29 8k
DeepSeek Flash Latest~deepseek$0.13$0.006$0.50 1,048k
Qwen3 32Bqwen$0.13$0.080$0.28 131k
Seed 1.6 Flashbytedance-seed$0.13$0.075$0.30 262k
gpt-oss-safeguard-20bopenai$0.13$0.075$0.30 131k
GPT-5 Nanoopenai$0.14$0.050$0.40 400k
GLM 4.7 Flashz-ai$0.15$0.060$0.40 200k
Gemma 3 27Bgoogle$0.15$0.080$0.35 131k
Ministral 3 8B 2512mistralai$0.15$0.15$0.15 262k
Qwen3 14Bqwen$0.15$0.12$0.24 40k
Llama 4 Scoutmeta-llama$0.15$0.10$0.30 1,310k
Voxtral Small 24B 2507mistralai$0.15$0.10$0.30 32k
Qwen3 30B A3B Instruct 2507qwen$0.15$0.10$0.30 262k
Step 3.5 Flashstepfun$0.15$0.10$0.30 262k
DeepSeek V4.1 Flashdeepseek$0.16$0.045$0.50 1,048k
Mercury 3inception$0.16$0.10$0.35 1,000k
Particle-1particle-ai$0.16$0.050$0.50 1,048k
Seed-2.0-Minibytedance-seed$0.18$0.10$0.40 262k
Gemini 2.5 Flash Litegoogle$0.18$0.10$0.40 1,048k
GPT-4.1 Nanoopenai$0.18$0.10$0.40 1,047k
MiMo-V2.6-Flashxiaomi$0.18$0.14$0.28 1,050k
Llama Guard 4 12Bmeta-llama$0.18$0.18$0.18 163k
Ternary Bonsai 2 27Bprism-ml$0.18$0.075$0.50 262k
Qwen3.5-9Bqwen$0.19$0.17$0.25 262k
Claude Haiku 5.5anthropic$0.20$0.10$0.50 1,000k
Ministral 3 14B 2512mistralai$0.20$0.20$0.20 262k
Nemotron 3.5 Content Safetynvidia$0.20$0.20$0.20 131k
GPT-6 Lunaopenai$0.20$0.10$0.50 1,050k
GPT-6 Luna Proopenai$0.20$0.10$0.50 1,050k
Claude Haiku Latest~anthropic$0.20$0.10$0.50 1,000k
GPT Luna Latest~openai$0.20$0.10$0.50 1,050k
LFM2.5-24B-A2Bliquid$0.21$0.050$0.70 128k
Qwen3 30B A3Bqwen$0.21$0.12$0.50 40k
Qwen3.8 Flashqwen$0.23$0.15$0.47 1,000k
Qwen3.8 Omni Flashqwen$0.23$0.15$0.47 1,000k
Hy3tencent$0.23$0.13$0.53 262k
Nemotron 3.5 Super VLnvidia$0.24$0.15$0.50 1,048k
GLM 5.3 Flashz-ai$0.24$0.15$0.50 1,048k
Hunyuan A13B Instructtencent$0.25$0.14$0.57 131k
Gemma 4 31Bgoogle$0.25$0.20$0.40 262k
Command R (08-2024)cohere$0.26$0.15$0.60 128k
DeepSeek V4.1 Flash 1017deepseek$0.26$0.15$0.60 1,048k
MiniMax M3.1 Flashminimax$0.26$0.15$0.60 1,048k
Mistral Small 4mistralai$0.26$0.15$0.60 262k
GPT-4o-miniopenai$0.26$0.15$0.60 128k
GPT-4o-mini (2024-07-18)openai$0.26$0.15$0.60 128k
gpt-oss-120bopenai$0.26$0.15$0.60 131k
Qwen3 Coder 30B A3B Instructqwen$0.26$0.15$0.60 262k
Qwen3 VL 30B A3B Instructqwen$0.26$0.15$0.60 262k
Solar Pro 4upstage$0.26$0.15$0.60 524k
Llama 3.3 70B Instructmeta-llama$0.28$0.20$0.52 131k
Hy3 previewtencent$0.29$0.18$0.60 262k
DeepSeek V3.2deepseek$0.29$0.26$0.38 163k
Qwen3 Coder Nextqwen$0.29$0.12$0.80 262k
Sabamistralai$0.30$0.20$0.60 32k
Qwen3.6 35B A3Bqwen$0.30$0.10$0.90 262k
ricursiveAI/Ripple-65B-Previewricursiveai$0.30$0.20$0.60 1,048k
DeepSeek V3.2 Expdeepseek$0.30$0.27$0.41 163k
Qwen3 235B A22B Instruct 2507qwen$0.31$0.14$0.80 262k
GLM 4.5 Airz-ai$0.31$0.13$0.85 131k
DeepSeek V4 Flash Vision Expdeepseek$0.32$0.22$0.65 1,048k
Qwen3 Next 80B A3B Instructqwen$0.34$0.090$1.10 262k
Cydonia 24B V4.1thedrummer$0.35$0.30$0.50 131k
Qwen3.5-35B-A3Bqwen$0.35$0.14$1.00 262k
Qwen2.5 72B Instructqwen$0.37$0.36$0.40 32k
Uncensoredcognitivecomputations$0.38$0.20$0.90 128k
Mercury 2inception$0.38$0.25$0.75 128k
Qwen3 VL 8B Instructqwen$0.38$0.25$0.75 262k
LFM2.5-2.6Bliquid$0.39$0.35$0.50 128k
Qwen-Plusqwen$0.39$0.26$0.78 1,000k
Qwen3 Coder Flashqwen$0.39$0.20$0.97 1,000k
UnslopNemo 12Bthedrummer$0.40$0.40$0.40 1,024k
Mistral Small 3.1 24Bmistralai$0.40$0.35$0.56 128k
GLM 5.3z-ai$0.40$0.070$1.40 1,048k
GLM Latest~z-ai$0.40$0.070$1.40 1,048k
Qwen3.6 Flashqwen$0.42$0.19$1.12 1,000k
ReMM SLERP 13Bundi95$0.42$0.35$0.65 6k
DeepSeek V3.1deepseek$0.42$0.25$0.95 163k
MiniMax-01minimax$0.43$0.20$1.10 1,000k
Beam 1.0 501B A23Breflection$0.44$0.25$1.00 1,048k
Step 3.7 Flashstepfun$0.44$0.20$1.15 262k
MiniMax M2.5minimax$0.44$0.27$0.95 204k
MiniMax M2minimax$0.45$0.26$1.02 204k
Codestral 2508mistralai$0.45$0.30$0.90 256k
GLM 4.6Vz-ai$0.45$0.30$0.90 131k
GPT-5.6 Lunaopenai$0.45$0.20$1.20 1,050k
GPT-5.6 Luna Proopenai$0.45$0.20$1.20 1,050k
DeepSeek V3deepseek$0.45$0.26$1.03 163k
DeepSeek V3.1 Terminusdeepseek$0.45$0.27$1.00 163k
GPT-5.4 Nanoopenai$0.46$0.20$1.25 400k
Qwen3 VL 30B A3B Thinkingqwen$0.47$0.29$1.00 262k
Qwen3 Coder 480B A35Bqwen$0.47$0.30$1.00 262k
Perceptron Mk1perceptron$0.49$0.15$1.50 32k
Perceptron Mk1.5perceptron$0.49$0.15$1.50 36k
Weaver (alpha)mancer$0.49$0.40$0.75 8k
DeepSeek V3 0324deepseek$0.50$0.29$1.14 163k
Llama 4 Maverickmeta-llama$0.51$0.35$1.00 524k
LongCat 2.0meituan$0.52$0.30$1.20 1,048k
Muse Glimmer 30Bmeta$0.52$0.30$1.20 131k
MiniMax M2-herminimax$0.52$0.30$1.20 65k
MiniMax M2.1minimax$0.52$0.30$1.20 204k
MiniMax M2.7minimax$0.52$0.30$1.20 204k
MiniMax M3minimax$0.52$0.30$1.20 1,048k

US dollars as listed on 2026-11-05; the 150 cheapest of 359 paid models shown. Free and variable-priced routes are left out. Some models charge more above a prompt size (often 200k tokens); the base rate is shown. Batch and cached-input discounts are not included.