modelbenchmark.io
All hosts

huggingface

65 models listed here. Prices are this host's, not the vendor list price.

DeepSeek V3.2164K$0.28$0.40
DeepSeek V4 Flash1M$0.14$0.28
DeepSeek V4 Pro1M$0.435$0.87
DeepSeek-R164K$0.70$2.50
DeepSeek-V3-0324164K$0.27$1.12
DeepSeek-V3.1131K$0.27$1.00
Gemma 4 26B A4B IT262K$0.13$0.40
Gemma 4 31B IT262K$0.14$0.40
GLM-4.5131K$0.60$2.20
GLM-4.5-Air131K$0.13$0.85
GLM-4.5V66K$0.60$1.80
GLM-4.6205K$0.55$2.20
GLM-4.6V-Flash131K$0.30$0.90
GLM-4.7205K$0.60$2.20
GLM-4.7-Flash200Kfreefree
GLM-5203K$1.00$3.20
GLM-5.1203K$1.00$3.20
GLM-5.2262K$1.40$4.40
GLM-5.31M$1.40$4.40
GLM-5.3-Flash1M$0.15$0.50
gpt-oss-120b131K$0.25$0.69
gpt-oss-20b131K$0.10$0.50
Hy3262K$0.14$0.58
Inkling1M$1.00$4.05
Inkling Small Thinking524K$0.50$1.20
Kimi K2 0905262K$1.00$3.00
Kimi K2 Thinking262K$0.60$2.50
Kimi K2.5262K$0.60$3.00
Kimi K2.6262K$0.95$4.00
Kimi K2.7 Code262K$0.95$4.00
Kimi K31M$3.00$15.00
Llama 3.1 8B Instruct131K$0.06$0.06
Llama 3.3 70B Instruct131K$0.59$0.79
MiMo V2.5 Pro1M$1.00$3.00
MiMo V2.5 Thinking262K$0.40$2.00
Mimo-V2-Flash262K$0.10$0.30
MiniMax-M2205K$0.30$1.20
MiniMax-M2.1205K$0.30$1.20
MiniMax-M2.5205K$0.30$1.20
MiniMax-M2.7205K$0.30$1.20
MiniMax-M3524K$0.30$1.20
Qwen2.5-Coder 32B Instruct131K$0.06$0.20
Qwen3 235b A22B Instruct 2507262K$0.855$2.565
Qwen3 235B A22B Thinking 2507262K$0.30$3.00
Qwen3 235B-A22B41K$0.20$0.80
Qwen3 30B A3B41K$0.12$0.50
Qwen3 32B131K$0.29$0.59
Qwen3 Coder Next262K$0.20$1.50
Qwen3 VL 235B A22B Instruct131K$0.30$1.50
Qwen3 VL 235B A22B Thinking131K$0.98$3.95
Qwen3-Coder 30B-A3B Instruct262K$0.07$0.26
Qwen3-Coder 480B-A35B Instruct262K$2.00$2.00
Qwen3-Next 80B-A3B (Thinking)262K$0.30$2.00
Qwen3-Next 80B-A3B Instruct262K$0.25$1.00
Qwen3.5 122B-A10B262K$0.40$3.20
Qwen3.5 27B262K$0.30$2.40
Qwen3.5 35B-A3B262K$0.25$2.00
Qwen3.5 397B-A17B262K$0.60$3.60
Qwen3.5 9B262K$0.17$0.25
Qwen3.6 27B262K$0.47$3.19
Qwen3.6 35B-A3B262K$0.15$0.95
Qwen3.8 2.4T A95B262K$2.50$6.25
Qwen3.8 27B262K$0.40$3.00
Step 3.7 Flash262K$0.20$1.15
Stepfun/Step-3.5 Flash262K$0.10$0.30