> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gpuhub.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

> Access GPUhub-hosted open-source models and route requests to closed-source models through one unified AI gateway.

You can call supported models through a compatible API, monitor usage, and pay based on actual consumption.

![Claude Code](https://mintcdn.com/gpuhub/GEB8Gf9uDczdNFr-/images/ide-agents-claude-code-icon.png?fit=max\&auto=format\&n=GEB8Gf9uDczdNFr-\&q=85\&s=619cd3f258c8dfc724b94ac2b85f2721)

![ChatGPT](https://mintcdn.com/gpuhub/szsKW_2Y2u2gI8Hg/images/ide-agents-chatgpt-icon.png?fit=max\&auto=format\&n=szsKW_2Y2u2gI8Hg\&q=85\&s=f81f568247a8fba9b94aea35b4993b51)

![Codex](https://mintcdn.com/gpuhub/GEB8Gf9uDczdNFr-/images/ide-agents-codex-icon.png?fit=max\&auto=format\&n=GEB8Gf9uDczdNFr-\&q=85\&s=e58c40da00bcc781ce797aeb90912b10)

![Gemini](https://mintcdn.com/gpuhub/szsKW_2Y2u2gI8Hg/images/ide-agents-gemini-icon.png?fit=max\&auto=format\&n=szsKW_2Y2u2gI8Hg\&q=85\&s=38f930a55beb4669c5dbf334ac1578e2)

![GLM](https://mintcdn.com/gpuhub/QVKtRg06DOo-ILOw/images/ide-agents-glm-icon.png?fit=max\&auto=format\&n=QVKtRg06DOo-ILOw\&q=85\&s=d67680207ed1c82e36ae43b1eab90d06)

![DeepSeek](https://mintcdn.com/gpuhub/szsKW_2Y2u2gI8Hg/images/ide-agents-deepseek-icon.png?fit=max\&auto=format\&n=szsKW_2Y2u2gI8Hg\&q=85\&s=5757caf5876c27e9c4f41992f30470b7)

![Qwen](https://mintcdn.com/gpuhub/szsKW_2Y2u2gI8Hg/images/ide-agents-qwen-icon.png?fit=max\&auto=format\&n=szsKW_2Y2u2gI8Hg\&q=85\&s=548de5f1fff11d866ca0849d0af50155)

![MiniMax](https://mintcdn.com/gpuhub/szsKW_2Y2u2gI8Hg/images/ide-agents-minimax-icon.png?fit=max\&auto=format\&n=szsKW_2Y2u2gI8Hg\&q=85\&s=5239692aeda633a69eea42bf332afd80)

> [!NOTE]
>
> Model availability, context length, and final prices may vary by model. Use the prices displayed in the console as the source of truth before starting production traffic.

## Supported Model Types

AI Gateway supports multiple categories of models for common AI workloads.

| Model Type | Typical Use Cases | Billing Unit |
| - | - | - |
| Language models | Chat, reasoning, coding, summarization, tool calling, and structured output | Input and output tokens |
| Long-context language models | Document analysis, large codebase analysis, and retrieval-augmented generation | Input and output tokens, sometimes tiered by context size |
| Claude-series models | Chat, coding, reasoning, and workflows that use prompt caching | Input tokens, output tokens, cache writes, and cache reads |

## Pricing

**AI Gateway provides two service plans**: Enterprise for production workloads and Developer for individual or experimental use. Model prices are listed in USD. Always use the unit prices displayed in the console as the source of truth.

> **Enterprise**
>
> Production-grade API access for enterprise workloads, with priority capacity, higher service stability, and dedicated support. Suitable for commercial applications, high-volume usage, and business-critical AI services.

> **Developer**
>
> Affordable API access for individual developers, testing, and non-critical workloads. Powered by shared capacity, with best-effort availability and performance that may vary depending on resource availability.

![](https://mintcdn.com/gpuhub/CYYSiRgUWABjTblG/images/ai-gateway-token.png?fit=max\&auto=format\&n=CYYSiRgUWABjTblG\&q=85\&s=500c08f50f2d4b419002769fa41e293e)

> [!NOTE]
>
> The prices below are placeholders used to illustrate each billing formula. They do not represent actual model prices.

### Language Models

General language models are billed by token usage.

| Usage Type | Unit Price |
| - | - |
| Input tokens | `$XX.XX` / 1M tokens |
| Output tokens | `$YY.YY` / 1M tokens |

Billing formula:

```text theme={null}
Total cost =
  (input tokens / 1,000,000 × $XX.XX)
+ (output tokens / 1,000,000 × $YY.YY)
```

### Tiered Context Pricing

Some language models select a pricing tier based on the total number of input tokens in a request. After the tier is selected, its input and output prices apply to the entire request.

| Context Tier | Input Tokens per Request | Input Token Price | Output Token Price |
| - | - | - | - |
| Standard context | Up to the model's tier threshold | `$XX.XX` / 1M tokens | `$YY.YY` / 1M tokens |
| Extended context | Above the model's tier threshold | `$AA.AA` / 1M tokens | `$BB.BB` / 1M tokens |

Standard-context formula:

```text theme={null}
Total cost =
  (input tokens / 1,000,000 × $XX.XX)
+ (output tokens / 1,000,000 × $YY.YY)
```

Extended-context formula:

```text theme={null}
Total cost =
  (input tokens / 1,000,000 × $AA.AA)
+ (output tokens / 1,000,000 × $BB.BB)
```

The exact threshold and prices vary by model and are displayed in the console.

### Claude-Series Prompt Caching

Claude-series models may include prompt caching charges in addition to normal input and output token charges.

| Usage Type | Unit Price |
| - | - |
| Input tokens | `$XX.XX` / 1M tokens |
| Output tokens | `$YY.YY` / 1M tokens |
| Cache write, 5-minute TTL | `$MM.MM` / 1M tokens |
| Cache write, 1-hour TTL | `$NN.NN` / 1M tokens |
| Cache read | `$ZZ.ZZ` / 1M tokens |

Billing formula:

```text theme={null}
Total cost =
  (input tokens / 1,000,000 × $XX.XX)
+ (output tokens / 1,000,000 × $YY.YY)
+ (5-minute cache write tokens / 1,000,000 × $MM.MM)
+ (1-hour cache write tokens / 1,000,000 × $NN.NN)
+ (cache read tokens / 1,000,000 × $ZZ.ZZ)
```

## Usage Notes

* Check the console for the latest model list, supported parameters, context limits, and real-time prices.
* For language models, estimate cost from both input and output tokens. Long prompts, retrieved documents, and tool results can increase input token usage.
* For tiered-context models, the input token count determines which price pair applies to the entire request.
* For cached prompts, cache writes and cache reads may appear as separate billable usage types.
* Use rate limits and budget controls when integrating AI Gateway into production applications.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.