inference.net API pricing

43 models from inference.net, verified 2026-08-30. Official pricing page →

Official page. Fetched directly from the provider's official pricing page and read off it.

Models and prices

ModelTierContext$/1M in$/1M out$/1M cache read
Claude Fable 5Flagship1M$10.00$50.00$1.00
Claude Opus 4.6Flagship1M$5.00$25.00$0.50
Claude Opus 4.7Flagship1M$5.00$25.00$0.50
Claude Opus 4.8Flagship1M$5.00$25.00$0.50
Claude Opus 5Flagship1M$5.00$25.00$0.50
DeepSeek V4 ProFlagship1.05M$0.435$0.87$0.00363
DeepSeek V4 Pro (0813)Flagship1.05M$1.32$3.96$0.044
Gemini 2.5 ProFlagship1.05M$1.25$10.00$0.125
Gemini 3.1 Pro PreviewFlagship1.05M$2.00$12.00$0.20
GLM-5.2Flagship1M$1.30$4.40$0.20
GLM-5.2 FastFlagship1M$2.60$8.80$0.40
GLM-5.3Flagship1M$1.75$5.50$0.325
GPT-5.4Flagship1.05M$2.50$15.00$0.25
GPT-5.5Flagship1.05M$5.00$30.00$0.50
GPT-5.6 SolFlagship1.05M$5.00$30.00$0.50
Kimi K3Flagship1.05M$3.00$15.00$0.30
Kimi K3 FastFlagship1.05M$4.50$22.50$0.45
Claude Sonnet 4.6Mid1M$3.00$15.00$0.30
Gemini 2.5 FlashMid1.05M$0.30$2.50$0.03
Gemini 3 Flash PreviewMid1.05M$0.50$3.00$0.05
Gemini 3.5 FlashMid1.05M$1.50$9.00$0.15
Gemini 3.6 FlashMid1.05M$1.50$7.50$0.15
Gemini 3.7 FlashMid1.05M$1.50$7.50$0.15
GPT-4.1Mid1.05M$2.00$8.00$0.50
GPT-4oMid128K$2.50$10.00$1.25
GPT-5.6 TerraMid1.05M$2.00$12.00$0.20
Grok 4.5Mid500K$2.00$6.00$0.30
Grok 4.6Mid500K$2.00$6.00$0.50
Claude Haiku 4.5Small200K$1.00$5.00$0.10
DeepSeek V4 FlashSmall164K$0.14$0.28$0.0028
DeepSeek V4 Flash (0731)Small256K$0.168$0.336$0.0336
Gemini 2.5 Flash LiteSmall1.05M$0.10$0.40$0.01
Gemini 3.1 Flash LiteSmall1.05M$0.25$1.50$0.025
Gemini 3.5 Flash-LiteSmall1.05M$0.30$2.50$0.03
GLM-5.3 FlashSmall1M$0.54$1.80$0.108
GPT-4.1 MiniSmall1.05M$0.40$1.60$0.10
GPT-4.1 NanoSmall1.05M$0.10$0.40$0.025
GPT-4o MiniSmall128K$0.15$0.60$0.075
GPT-5 MiniSmall400K$0.25$2.00$0.025
GPT-5 NanoSmall400K$0.05$0.40$0.005
GPT-5.6 LunaSmall1.05M$0.20$1.20$0.02
schematron-v2-smallSmall128K$0.05$0.25$0.05
schematron-v2-turboSmall128K$0.03$0.15$0.03