serverless inference
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, or put the models marked included on the flat plan: $0.99 a month for 500 million input and 50 million output tokens. No instance to rent, no cold infrastructure to babysit.
| Model | Author | Context | Input / 1M | Cached input / 1M | Output / 1M |
|---|---|---|---|---|---|
| DeepSeek V4 Pro 0813 | DeepSeek | 1M | $1.32 | $0.13 | $3.96 |
| DeepSeek V4.1 Flash 1017IncludedVerifiedTTFT 2.2 s · 185 tok/s | DeepSeek | 1M | $0.07 | $0.0014 | $0.27 |
| GLM 5.2TTFT 1.8 s · 61 tok/s | Z.ai | 1M | $0.59 | $0.113 | $1.92 |
| GLM 5.3IncludedTTFT 6.8 s · 166 tok/s | Z.ai | 1M | $0.90 | $0.167 | $2.83 |
| GLM 5.3 FlashIncludedTTFT 3.3 s · 129 tok/s | Z.ai | 1M | $0.15 | $0.03 | $0.50 |
| GPT-OSS 120B | OpenAI | 128K | $0.15 | – | $0.60 |
| Kimi K3IncludedTTFT 13.3 s · 52 tok/s | Moonshot AI | 1M | $1.95 | $0.195 | $9.75 |
| Kimi K3.1 Pro | Moonshot AI | 1M | $2.00 | $0.20 | $10.00 |
| Minimax M3.1 Flash | MiniMax | 1M | $0.15 | $0.015 | $0.60 |
| Muse Glimmer 30B | Meta | 128K | $0.35 | $0.04 | $1.50 |
| Muse Spark Open 816B A42B | Meta | 1M | $1.25 | $0.15 | $4.25 |
| Qwen3.5 9B | Qwen | 256K | $0.17 | – | $0.25 |
| Qwen3.6 Plus | Qwen | 1M | $0.50 | – | $3.00 |
| Qwen3.7 Max | Qwen | 1M | $2.50 | $0.50 | $7.50 |
| Qwen3.7 Plus | Qwen | 1M | $0.32 | – | $1.28 |
| Qwen3.8 FlashVerified | Qwen | 1M | $0.15 | – | $0.47 |
| Qwen3.8 Max | Qwen | 1M | $2.00 | $0.25 | $6.00 |
Included means covered by the flat plan: $0.99 a month for 500 million input and 50 million output tokens across the included models. Every other model bills pay as you go.
| Model | Author | Price |
|---|---|---|
| Flash Image 2.5 | $0.039 per image | |
| Flash Image 3.1 | $0.047 per image | |
| Flash Image 3.1 Lite | $0.069 per image | |
| FLUX.1 Kontext Max | Black Forest Labs | $0.08 per output megapixel |
| FLUX.1 Kontext Pro | Black Forest Labs | $0.04 per output megapixel |
| FLUX.1.1 Pro | Black Forest Labs | $0.04 per output megapixel |
| FLUX.2 Dev | Black Forest Labs | $0.015 per image |
| FLUX.2 Flex | Black Forest Labs | $0.03 per image |
| FLUX.2 Max | Black Forest Labs | $0.07 per output megapixel |
| FLUX.2 Pro | Black Forest Labs | $0.03 per image |
| Gemini 3 Pro Image | $0.134 per image | |
| GPT Image 1.5 | OpenAI | $0.034 per image |
| GPT Image 2 | OpenAI | $0.053 per image |
| Qwen Image | Qwen | $0.0058 per image |
| Qwen Image 2.0 | Qwen | $0.035 per image |
| Qwen Image 2.0 Pro | Qwen | $0.075 per image |
| Seedream 3.0 | ByteDance | $0.018 per image |
| Seedream 4.0 | ByteDance | $0.03 per image |
| Seedream 5.0 Lite | ByteDance | $0.035 per image |
| Wan2.6 Image | Wan | $0.03 per image |
| Model | Author | Price |
|---|---|---|
| FLUX 3 | Black Forest Labs | $0.17 per second of video |
| Happyhorse 1.0 T2v | Alibaba | $0.24 per second of video |
| Happyhorse 1.1 T2v | Alibaba | $0.14 per second of video |
| Pixverse V5 | PixVerse | $0.06 per second of video |
| Seedance 1.0 Lite | ByteDance | $0.029 per second of video |
| Seedance 1.0 Pro | ByteDance | $0.113 per second of video |
| Seedance 2.0 | ByteDance | $0.16 per second of video |
| Seedance 2.5 | ByteDance | $0.115 per second of video |
| Vidu Q1 | Vidu | $0.044 per second of video |
| Vidu Q3 | Vidu | $0.098 per second of video |
| Vidu Q3 Turbo | Vidu | $0.195 per second of video |
| Wan2.7 T2v | Wan | $0.02 per second of video |
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: $0.99 a month carries 500 million input and 50 million output tokens across those models, 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.