serverless inference
Every model behind our OpenAI-compatible inference API, priced per use. Point your existing SDK at api.gpu.ai/v1 and pay per token or per image. No instance to rent, no cold infrastructure to babysit.
| Model | Author | Context | Input / 1M | Cached input / 1M | Output / 1M |
|---|---|---|---|---|---|
| GLM 5.2 | Z.AI | 198K | $1.54 | $0.286 | $4.84 |
| GLM 5.3 | Z.AI | 198K | $1.54 | $0.286 | $4.84 |
| GLM 5.3 Flash | Z.AI | 1024K | $0.17 | $0.033 | $0.55 |
| GPT-OSS 120B | OpenAI | 128K | $0.17 | — | $0.66 |
| Kimi K3 | Moonshot AI | 1024K | $3.30 | $0.330 | $16.50 |
| Kimi K3.1 Pro | Moonshot AI | 1024K | $2.20 | $0.220 | $11.00 |
| Minimax M3 | MiniMax | 500K | $0.33 | $0.066 | $1.32 |
| Minimax M3.1 Flash | MiniMax | 1024K | $0.17 | $0.017 | $0.66 |
| Muse Glimmer 30B | Meta | 128K | $0.39 | $0.044 | $1.65 |
| Muse Spark Open 816B A42B | Meta | 1024K | $1.38 | $0.165 | $4.68 |
| Qwen3.5 9B | Qwen | 256K | $0.19 | — | $0.28 |
| Qwen3.6 Plus | Qwen | 977K | $0.55 | — | $3.30 |
| Qwen3.7 Max | Qwen | 977K | $2.75 | $0.550 | $8.25 |
| Qwen3.7 Plus | Qwen | 977K | $0.35 | — | $1.41 |
| Qwen3.8 Flash | Qwen | 977K | $0.17 | — | $0.52 |
| Model | Author | Price |
|---|---|---|
| Flash Image 2.5 | $0.043 per image | |
| Flash Image 3.1 | $0.051 per image | |
| Flash Image 3.1 Lite | $0.076 per image | |
| FLUX.1 Kontext Max | Black Forest Labs | $0.088 per output megapixel |
| FLUX.1 Kontext Pro | Black Forest Labs | $0.044 per output megapixel |
| FLUX.1.1 Pro | Black Forest Labs | $0.044 per output megapixel |
| FLUX.2 Dev | Black Forest Labs | $0.017 per image |
| FLUX.2 Flex | Black Forest Labs | $0.033 per image |
| FLUX.2 Max | Black Forest Labs | $0.077 per output megapixel |
| FLUX.2 Pro | Black Forest Labs | $0.033 per image |
| Gemini 3 Pro Image | $0.147 per image | |
| GPT Image 1.5 | OpenAI | $0.037 per image |
| GPT Image 2 | OpenAI | $0.058 per image |
| Qwen Image | Qwen | $0.0064 per image |
| Qwen Image 2.0 | Qwen | $0.038 per image |
| Qwen Image 2.0 Pro | Qwen | $0.083 per image |
| Seedream 3.0 | ByteDance | $0.020 per image |
| Seedream 4.0 | ByteDance | $0.033 per image |
| Seedream 5.0 Lite | ByteDance | $0.038 per image |
| Wan2.6 Image | Wan | $0.033 per image |
| Model | Author | Price |
|---|---|---|
| FLUX 3 | Black Forest Labs | $0.187 per second of video |
| Hailuo 02 | MiniMax | $0.062 per second of video |
| Happyhorse 1.0 T2v | Alibaba | $0.264 per second of video |
| Happyhorse 1.1 T2v | Alibaba | $0.154 per second of video |
| Minimax H3 | MiniMax | $0.153 per second of video |
| Pixverse V5 | PixVerse | $0.066 per second of video |
| Seedance 1.0 Lite | ByteDance | $0.031 per second of video |
| Seedance 1.0 Pro | ByteDance | $0.124 per second of video |
| Seedance 2.0 | ByteDance | $0.176 per second of video |
| Seedance 2.5 | ByteDance | $0.127 per second of video |
| Vidu Q1 | Vidu | $0.048 per second of video |
| Vidu Q3 | Vidu | $0.107 per second of video |
| Vidu Q3 Turbo | Vidu | $0.214 per second of video |
| Wan2.7 T2v | Wan | $0.022 per second of video |
Every model is served through one OpenAI-compatible endpoint at https://api.gpu.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 subscriptions, no minimums, billed against your GPU.ai balance. 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.