# Grok API for Grok 4.7 and Imagine.

> Use Grok 4.7 through one OpenAI-compatible Outrun key. Grok 4.7 costs $0.09 in / $0.26 out per 1M tokens, 95% below xAI's list.

Outrun serves Grok 4.7 through one OpenAI-compatible API key. Grok 4.7 costs $0.09 per 1M input tokens and $0.26 per 1M output tokens. The same key also covers the Grok image and video models listed below. Outrun does not store your prompts or outputs on any Grok ID.

[Try Grok in the Playground](https://outrun.to/playground) [Get your API key](https://t.me/outrunAPI_Bot) [All Grok prices](https://outrun.to/grok-api#prices)

$0.10 free API credit for eligible new accounts.

1 model ID on one Outrun key

Lowest-priced model

[Grok 4.7](https://outrun.to/model/grok-4.7)

`grok-4.7`

**$0.09** in */* **$0.26** outper 1M tokens

**95%** below xAI's list output price *($0.26 vs $6.00)*

Endpoint

/v1/chat/completions

Format

OpenAI-compatible

Grok IDs

1

Input from

$0.09

Privacy

Zero at Outrun

## Which Grok model ID should I use?

Use `grok-4.7` for Grok 4.7. Keep the same key and base URL when you switch IDs. Each model name in the price table opens its own page with prices, capabilities and setup values.

- Lowest cost per input token`grok-4.7`$0.09 / $0.26

## How much does the Grok API cost on Outrun?

1 Grok text model is available on Outrun, starting at $0.09 per 1M input tokens. Every ID is billed per token from prepaid USD credit; the table lists every context and cache tier.

| Model | Input | Output | Cached input |
| --- | --- | --- | --- |
| [Grok 4.7](https://outrun.to/model/grok-4.7) `grok-4.7` up to 200k tokens | $0.09 | $0.26 | $0.03 |
| Grok 4.7, over 200k tokens | $0.17 | $0.51 | $0.05 |

Billed rates, rounded up to the cent, updated 2026-10-29. Cached input is part of input, not an extra charge. The [pricing page](https://outrun.to/discounted-ai-api) lists every model.

## How do the prices compare?

Standard-tier output rates against the official list prices the [pricing page](https://outrun.to/discounted-ai-api) cites.

| Model | Outrun | List price | Difference | Source |
| --- | --- | --- | --- | --- |
| [Grok 4.7](https://outrun.to/model/grok-4.7) `grok-4.7` | $0.09*/*$0.26 | $2.00*/*$6.00 | **95%** lower | [xAI](https://docs.x.ai/developers/models) |

## What else can I use with the same key?

Image, video and audio models have their own billing units and endpoints. Open a model page for its request format.

| Model | Kind | Rate |
| --- | --- | --- |
| [Grok Imagine Image](https://outrun.to/model/grok-imagine-image) `grok-imagine-image` | Image | $0.06 per image |
| [Grok Imagine Video](https://outrun.to/model/grok-imagine-video) `grok-imagine-video` | Video | $0.03 per second |
| [Grok Imagine Video 1.5 1080p](https://outrun.to/model/grok-imagine-video-1.5-1080p) `grok-imagine-video-1.5-1080p` | Video | $0.09 per second |
| [Grok TTS](https://outrun.to/model/grok-tts) `grok-tts` | Audio | $9.45 per 1M characters |

## How do I call the Grok API through Outrun?

Grok text models on Outrun use the OpenAI Chat Completions format, so the OpenAI SDKs and any OpenAI-compatible app work with your Outrun key and base URL.

1. 01
  ### Get your key
  Open the Telegram bot and copy your personal key. It works for Grok and every other Outrun model.
2. 02
  ### Set the base URL
  Use `https://api.outrun.to/v1` exactly as shown, without `/chat/completions`.
3. 03
  ### Send a Grok model ID
  Put the full ID, such as `grok-4.7`, in the `model` field.

**POST**/v1/chat/completions

```
curl https://api.outrun.to/v1/chat/completions \
  -H "Authorization: Bearer $OUTRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4.7",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'
```

Swap the model

Grok 4.7, up to 200k tokens **$0.09** in*/* **$0.26** outper 1M tokens [All Grok prices](https://outrun.to/grok-api#prices)

Keep your key in an environment variable, never in client-side code.

### Setup guides

- [OpenCode CLI](https://outrun.to/docs/setup/opencode)
- [API reference](https://outrun.to/docs/api)
- [Model documentation](https://outrun.to/docs/models)

## Does Outrun keep my Grok prompts?

No. Outrun does not store your prompts, images or outputs on any model, Grok included. For each request Outrun keeps only a usage record for billing: model, tokens and cost. API calls are never added to chat history.

[How Outrun handles your prompts](https://outrun.to/uncensored-ai-api#privacy)

## Grok API questions

The [model pages](https://outrun.to/model/) list every Grok ID with its current rate and setup values.

### Do I need a xAI account?

No. One Outrun key and one prepaid USD balance cover Grok and every other model on Outrun. You get the key from the Telegram bot, and eligible new accounts start with $0.10 in free credit.

### Which Grok model has the lowest input price?

Grok 4.7 starts at $0.09 per 1M input tokens and $0.26 per 1M output tokens.

### How do I switch models?

Keep your Outrun key and the API base URL, and change the model ID in your request. Each model page lists its prices and setup values.

### Can I try Grok for free?

Eligible new accounts start with $0.10 in free API credit. Usage is billed at the rates on this page, and the Playground lets you try any model in your browser.

## Keep exploring

- [Pricing **All 116 prices**](https://outrun.to/discounted-ai-api)
- [Models **Every model page**](https://outrun.to/model/)
- [Guide **Gemini API**](https://outrun.to/gemini-api)
- [Guide **Kimi API**](https://outrun.to/kimi-api)
- [Guide **GPT API**](https://outrun.to/gpt-api)
- [Playground **Try Grok in your browser**](https://outrun.to/playground)

---
Source: https://outrun.to/grok-api
Outrun: https://outrun.to/ | API base: https://api.outrun.to/v1 | Prices (JSON): https://api.outrun.to/pricing | Docs: https://outrun.to/docs/
