# Hyperouter

> Hyperouter is an OpenAI-compatible router for language, image and video models. One HTTP API and one prepaid USD balance give access to models from several providers. Each request goes to a healthy provider and is charged at that provider's list price, with no markup. The API base URL is https://api.hyperouter.app/v1. An MCP server for the dashboard is at https://api.hyperouter.app/mcp.

## Docs

- [Hyperouter API](https://hyperouter.app/docs.md): Hyperouter API reference: authentication, errors, models, chat completions, images, video, generations, model-specific parameters, moderation, webhooks, MCP and billing.

## Policies

- [Terms of Service](https://hyperouter.app/terms.md): The terms that govern your use of Hyperouter.
- [Privacy Policy](https://hyperouter.app/privacy.md): How Hyperouter collects, uses and protects your information.

## Models

- [Models](https://hyperouter.app/models/): Every public model on Hyperouter: context window, list price and a page with code to call it through the OpenAI SDK.
- [Grok 4.7 API](https://hyperouter.app/models/x-ai-grok-4-7): Grok 4.7 (x-ai/grok-4.7) through Hyperouter's OpenAI-compatible API: a 500K context window, $2.00 / $0.50 / $6.00 per 1M tokens (input / cached input / output), and code to call it.
- [Grok 4.6 API](https://hyperouter.app/models/x-ai-grok-4-6): Grok 4.6 (x-ai/grok-4.6) through Hyperouter's OpenAI-compatible API: a 500K context window, $2.00 / $0.50 / $6.00 per 1M tokens (input / cached input / output), and code to call it.
- [Grok 4.5 API](https://hyperouter.app/models/x-ai-grok-4-5): Grok 4.5 (x-ai/grok-4.5) through Hyperouter's OpenAI-compatible API: a 500K context window, $2.00 / $0.30 / $6.00 per 1M tokens (input / cached input / output), and code to call it.
- [Grok 4.3 API](https://hyperouter.app/models/x-ai-grok-4-3): Grok 4.3 (x-ai/grok-4.3) through Hyperouter's OpenAI-compatible API: a 1M context window, $1.25 / $0.20 / $2.50 per 1M tokens (input / cached input / output), and code to call it.
- [Grok Build 0.1 API](https://hyperouter.app/models/x-ai-grok-build-0-1): Grok Build 0.1 (x-ai/grok-build-0.1) through Hyperouter's OpenAI-compatible API: a 256K context window, $1.00 / $0.20 / $2.00 per 1M tokens (input / cached input / output), and code to call it.
- [DeepSeek V4.1 Flash API](https://hyperouter.app/models/deepseek-deepseek-v4-1-flash): DeepSeek V4.1 Flash (deepseek/deepseek-v4.1-flash) through Hyperouter's OpenAI-compatible API: a 1M context window, $0.15 / $0.003 / $0.60 per 1M tokens (input / cached input / output), and code to call it.
- [DeepSeek V4.1 Flash 1017 API](https://hyperouter.app/models/deepseek-deepseek-v4-1-flash-1017): DeepSeek V4.1 Flash 1017 (deepseek/deepseek-v4.1-flash-1017) through Hyperouter's OpenAI-compatible API: a 1M context window, $0.15 / $0.003 / $0.60 per 1M tokens (input / cached input / output), and code to call it.
- [GPT-6 Astra API](https://hyperouter.app/models/openai-gpt-6-astra): GPT-6 Astra (openai/gpt-6-astra) through Hyperouter's OpenAI-compatible API: a 272K context window, $10.00 / $1.00 / $50.00 per 1M tokens (input / cached input / output), and code to call it.
- [GPT-6.1 Sol API](https://hyperouter.app/models/openai-gpt-6-1-sol): GPT-6.1 Sol (openai/gpt-6.1-sol) through Hyperouter's OpenAI-compatible API: a 272K context window, $2.00 / $0.10 / $10.00 per 1M tokens (input / cached input / output), and code to call it.
- [GLM-5.3 API](https://hyperouter.app/models/z-ai-glm-5-3): GLM-5.3 (z-ai/glm-5.3) through Hyperouter's OpenAI-compatible API: a 1M context window, $1.40 / $0.26 / $4.40 per 1M tokens (input / cached input / output), and code to call it.
- [Face Detect API](https://hyperouter.app/models/lumina-face-detect): Face Detect (lumina/face-detect) through Hyperouter's OpenAI-compatible API: $0.0013 per request, and code to call it.
- [Grok Imagine Image API](https://hyperouter.app/models/x-ai-grok-imagine-image): Grok Imagine Image (x-ai/grok-imagine-image) through Hyperouter's OpenAI-compatible API: Generate and edit. Up to 10 images, up to 5 input images. $0.02 per image. Code to call it with the OpenAI SDK.
- [Grok Imagine Image 2.0 API](https://hyperouter.app/models/x-ai-grok-imagine-image-2-0): Grok Imagine Image 2.0 (x-ai/grok-imagine-image-2.0) through Hyperouter's OpenAI-compatible API: Generate and edit, as above. From $0.04 per image. Code to call it with the OpenAI SDK.
- [Qwen Image 2.0 API](https://hyperouter.app/models/qwen-qwen-image-2-0): Qwen Image 2.0 (qwen/qwen-image-2.0) through Hyperouter's OpenAI-compatible API: Generate and edit (1 to 3 input images). n 1 to 6. $0.035 per image. Code to call it with the OpenAI SDK.
- [Seedream 5.0 Flash API](https://hyperouter.app/models/bytedance-seedream-5-0-flash): Seedream 5.0 Flash (bytedance/seedream-5.0-flash) through Hyperouter's OpenAI-compatible API: Generate and edit (1 to 10 input images). One 2K image per request, no watermark. $0.018 per image. Code to call it with the OpenAI SDK.
- [Seedream 5.0 Lite API](https://hyperouter.app/models/bytedance-seedream-5-0-lite): Seedream 5.0 Lite (bytedance/seedream-5.0-lite) through Hyperouter's OpenAI-compatible API: Generate and edit, as above. $0.035 per image. Code to call it with the OpenAI SDK.
- [Grok Imagine Video API](https://hyperouter.app/models/x-ai-grok-imagine-video): Grok Imagine Video (x-ai/grok-imagine-video) through Hyperouter's OpenAI-compatible API: Text, image or video input. 15 s at most. Supports edit. From $0.050 per second of video. Code to call it with the OpenAI SDK.
- [Grok Imagine Video 1.5 API](https://hyperouter.app/models/x-ai-grok-imagine-video-1-5): Grok Imagine Video 1.5 (x-ai/grok-imagine-video-1.5) through Hyperouter's OpenAI-compatible API: Text, image or reference input. 15 s at most. From $0.080 per second of video. Code to call it with the OpenAI SDK.
- [Grok Imagine Video 1.5 Lite API](https://hyperouter.app/models/x-ai-grok-imagine-video-1-5-lite): Grok Imagine Video 1.5 Lite (x-ai/grok-imagine-video-1.5-lite) through Hyperouter's OpenAI-compatible API: As above, smaller and cheaper. From $0.020 per second of video. Code to call it with the OpenAI SDK.
- [Seedance 2.0 API](https://hyperouter.app/models/bytedance-seedance-2-0): Seedance 2.0 (bytedance/seedance-2.0) through Hyperouter's OpenAI-compatible API: Text, first and last frame, or reference image input, optional audio. 4 to 15 s. 480p, 720p, 1080p or 4K. From $0.0431892 per second of video. Code to call it with the OpenAI SDK.
- [Seedance 2.0 Fast API](https://hyperouter.app/models/bytedance-seedance-2-0-fast): Seedance 2.0 Fast (bytedance/seedance-2.0-fast) through Hyperouter's OpenAI-compatible API: Text, first and last frame, or reference image input, optional audio. 4 to 15 s. 480p or 720p. From $0.0331452 per second of video. Code to call it with the OpenAI SDK.
- [Seedance 2.0 Mini API](https://hyperouter.app/models/bytedance-seedance-2-0-mini): Seedance 2.0 Mini (bytedance/seedance-2.0-mini) through Hyperouter's OpenAI-compatible API: Text, first and last frame, or reference image input, optional audio. 4 to 15 s. 480p or 720p. From $0.0210924 per second of video. Code to call it with the OpenAI SDK.
- [Seedance 2.5 API](https://hyperouter.app/models/bytedance-seedance-2-5): Seedance 2.5 (bytedance/seedance-2.5) through Hyperouter's OpenAI-compatible API: Text, first and last frame, or reference image input, optional audio. 4 to 15 s. 480p, 720p or 1080p. From $0.0642816 per second of video. Code to call it with the OpenAI SDK.
- [Berry 1.0 API](https://hyperouter.app/models/lumina-berry-1-0): Berry 1.0 (lumina/berry-1.0) through Hyperouter's OpenAI-compatible API: Text, image or reference input, optional audio. 30 s at most. 480p, 720p or 1080p. From $0.050 per second of video. Code to call it with the OpenAI SDK.
- [MiniMax H3 API](https://hyperouter.app/models/minimax-minimax-h3): MiniMax H3 (minimax/minimax-h3) through Hyperouter's OpenAI-compatible API: Text, first and last frame, or reference image input, no audio. 4 to 15 s, at 768p or 2K. From $0.080 per second of video. Code to call it with the OpenAI SDK.
- [Wan 3.0 API](https://hyperouter.app/models/alibaba-wan3-0): Wan 3.0 (alibaba/wan3.0) through Hyperouter's OpenAI-compatible API: Text, image or reference input, optional audio. 30 s at most. 480p, 720p or 1080p. From $0.050 per second of video. Code to call it with the OpenAI SDK.

## Use cases

- [Use cases](https://hyperouter.app/cases/): Pipelines that chain chat, image and video models: type one sentence or paste one photo, and get finished stills and film. Each one forks into your dashboard and runs at list prices.
- [One person, four scenes](https://hyperouter.app/cases/one-person-four-scenes): A portrait, then three edits that keep her face.
- [Homecoming](https://hyperouter.app/cases/homecoming): One still, then eight seconds of film with sound.
- [An old photo comes alive](https://hyperouter.app/cases/old-photo-alive): Restore and colourise an old photo, then animate it.
- [Rice terraces](https://hyperouter.app/cases/rice-terraces): One still of the terraces, then six seconds of motion.

## Optional

- [All pages in one file](https://hyperouter.app/llms-full.txt): The full text of every Markdown page above, for loading into a context window.