300 million tokens. $2.99 a month.See the subscription  

serverless inference

AI model API pricing

Every model behind our OpenAI-compatible inference API, priced per use. Point your existing SDK at api.deeprelay.ai/v1 and pay per token or per image. No instance to rent, no cold infrastructure to babysit.

Chat / LLM models

12 models
ModelAuthorContextInput / 1MCached input / 1MOutput / 1M
GLM 5.2Z.ai198K$1.48$0.276$4.66
GLM 5.3Z.ai198K$1.48$0.276$4.66
GLM 5.3 FlashZ.ai1024K$0.16$0.032$0.53
GPT-OSS 120BOpenAI128K$0.16$0.64
Kimi K2.6Moonshot AI256K$1.01$0.17$4.24
Kimi K2.7 CodeMoonshot AI256K$1.01$0.201$4.24
Kimi K3Moonshot AI1024K$3.18$0.318$15.90
Llama 3.3 70B InstructMeta32K$1.10$1.10
Minimax M3MiniMax512K$0.32$0.064$1.27
Muse Glimmer 30BMeta128K$0.37$0.042$1.59
Qwen3.5 9BQwen256K$0.18$0.27
Qwen3.8 2.4t A95BQwen986K$2.12$0.265$6.36

Image generation models

23 models
ModelAuthorPrice
Flash Image 2.5Google$0.041 per image
Flash Image 3.1Google$0.049 per image
Flash Image 3.1 LiteGoogle$0.073 per image
FLUX.1 Kontext MaxBlack Forest Labs$0.085 per output megapixel
FLUX.1 Kontext ProBlack Forest Labs$0.042 per output megapixel
FLUX.1.1 ProBlack Forest Labs$0.042 per output megapixel
FLUX.2 DevBlack Forest Labs$0.016 per image
FLUX.2 FlexBlack Forest Labs$0.032 per image
FLUX.2 MaxBlack Forest Labs$0.074 per output megapixel
FLUX.2 ProBlack Forest Labs$0.032 per image
Gemini 3 Pro ImageGoogle$0.142 per image
GPT Image 1.5OpenAI$0.036 per image
GPT Image 2OpenAI$0.056 per image
Imagen 4.0 FastGoogle$0.021 per image
Imagen 4.0 PreviewGoogle$0.042 per image
Imagen 4.0 UltraGoogle$0.064 per image
Qwen ImageQwen$0.0061 per image
Qwen Image 2.0Qwen$0.037 per image
Qwen Image 2.0 ProQwen$0.08 per image
Seedream 3.0ByteDance$0.019 per image
Seedream 4.0ByteDance$0.032 per image
Seedream 5.0 LiteByteDance$0.037 per image
Wan2.6 ImageWan$0.032 per image

Video generation models

18 models
ModelAuthorPrice
FLUX 3Black Forest Labs$0.18 per second of video
Hailuo 02MiniMax$0.059 per second of video
Happyhorse 1.0 T2vAlibaba$0.254 per second of video
Happyhorse 1.1 T2vAlibaba$0.148 per second of video
Kling 2.1 StandardKling$0.039 per second of video
Minimax H3MiniMax$0.147 per second of video
Pixverse V5PixVerse$0.063 per second of video
Seedance 1.0 LiteByteDance$0.03 per second of video
Seedance 1.0 ProByteDance$0.12 per second of video
Seedance 2.0ByteDance$0.17 per second of video
Seedance 2.5ByteDance$0.122 per second of video
Sora 2OpenAI$0.106 per second of video
Sora 2 ProOpenAI$0.398 per second of video
Veo 2.0Google$0.53 per second of video
Vidu Q1Vidu$0.047 per second of video
Vidu Q3Vidu$0.103 per second of video
Vidu Q3 TurboVidu$0.207 per second of video
Wan2.7 T2vWan$0.021 per second of video

How this pricing works

Every model is served through one OpenAI-compatible endpoint at https://api.deeprelay.ai/v1. Chat models bill per input and output token; the part of a prompt a partner serves from its prompt cache bills at the lower cached-input rate where one is listed (a dash means the model has no cached rate and every prompt token bills at the input rate). Image and video models bill per generation. Prices are the live catalog rates, the same figures the API and the console bill against: no minimums, billed against your deeprelay balance as you go. Models marked included ride the flat plan instead: $2.99 a month carries 300M input and 30M output tokens across those models, weighted by each model's usage factor, and anything past the allowance falls back to the rates above. Models marked economy trade a cold start of roughly 30–60 seconds for a lower rate. This page refreshes every few minutes from the live model catalog.