Host

Deep Infra

Models and prices (opens in a new tab) ↗

Models59

Ranked43

Top index74.0Claude Fable 5

Lowest output$0.14GPT-OSS 20B

Models

Highest index first

ModelIndexInput / 1MOutput / 1MContext

Claude Fable 574.0$10.00$50.001M

MiMo-V2.6-Pro70.2$0.43$0.871.05M

DeepSeek V4.1 Flash 101768.5$0.20$0.601.05M

Step 5 PreviewDeprecated68.4$1.00$2.701.05M

Kimi K366.9$2.85$14.251.05M

Hy4 preview66.4$0.834$2.501.05M

GLM-5.365.8$0.90$4.001.05M

DeepSeek V4 Pro 081365.5$1.30$2.601.05M

MiMo-V2.6-Flash64.3$0.14$0.281.05M

GLM-5.3-Flash63.1$0.15$0.501.05M

DeepSeek V4 Flash 073161.9$0.06$0.181.05M

GLM-5.260.6$0.75$2.401.05M

Qwen3.7 Max60.5$2.50$7.50256K

DeepSeek V4 Flash Vision Exp60.4$0.44$1.321.05M

Qwen3.8-27B59.2$0.20$2.50262K

Kimi K2.658.2$0.75$3.50262K

Kimi K2.7 CodeDeprecated57.7$0.68$3.40262K

DeepSeek V4 Pro 042357.6$1.30$2.601.05M

MiMo-V2.5-ProDeprecated56.3$1.00$3.001.05M

GLM-5.1Deprecated56.0$1.05$3.50203K

MiniMax M355.7$0.28$1.10524K

Step 3.7 FlashDeprecated55.3$0.20$1.15262K

Inkling-Small55.1$0.45$1.20524K

MiMo-V2.5Deprecated54.8$0.14$0.28262K

InklingDeprecated54.8$0.95$4.05524K

Kimi K2.5Deprecated52.2$0.45$2.25262K

Qwen3.6-27B52.1$0.32$3.20262K

Qwen3.5-122B-A10BDeprecated51.9$0.29$2.40262K

GLM-5Deprecated51.6$0.60$2.08203K

Qwen3.5-27B51.3$0.26$2.60262K

MiniMax M2.7Deprecated51.2$0.25$1.00197K

Qwen3.6-35B-A3B50.6$0.10$0.95262K

MiniMax M2.5Deprecated50.2$0.15$1.15197K

GLM-4.750.0$0.40$1.75203K

Qwen3.5-35B-A3B49.4$0.14$1.00262K

DeepSeek-R1-052844.6$0.50$2.15164K

DeepSeek V3.244.2$0.26$0.38164K

GPT-OSS 120B43.4$0.037$0.17131K

Qwen3 235B 250742.3$0.09$0.55262K

GLM-4.641.8$0.50$2.00203K

GPT-OSS 20B41.7$0.03$0.14131K

Llama 4 MaverickDeprecated34.4$0.20$0.801.05M

Llama 4 Scout26.8$0.10$0.30328K

DeepSeek V4 Flash 0423Unranked$0.09$0.181.05M

GLM-4.7-FlashDeprecatedUnranked$0.06$0.40203K

Hy3DeprecatedUnranked$0.13$0.53262K

Llama 3.3 70B InstructUnranked$0.10$0.32131K

Llama Guard 4 12BUnranked$0.18$0.18164K

Nemotron 3 Nano 30B A3BDeprecatedUnranked$0.05$0.20262K

Qwen3 30B A3BUnranked$0.12$0.5041K

Qwen3 32BUnranked$0.08$0.2841K

Qwen3 Next 80B A3B InstructUnranked$0.09$1.10262K

Qwen3 VL 235B A22B InstructUnranked$0.20$0.88262K

Qwen3 VL 30B A3B InstructUnranked$0.15$0.60262K

Qwen3.5 397B A17BUnranked$0.45$3.00262K

Qwen3.5 9BUnranked$0.10$0.15262K

Qwen3.8 2.4T A95BDeprecatedUnranked$2.00$6.00262K

Qwen3.8 FlashUnranked$0.113$0.3821M

Seed-2.0-MiniUnranked$0.10$0.40256K

Models with a page on this site. List prices in US dollars per 1M tokens, from models.dev (MIT). Each model page compares all its providers.