# Grok Build 0.1

Canonical page: https://agentsky.dev/models/xai/grok-build-0.1
JSON record: https://gateway.agentsky.dev/v1/models/xai/grok-build-0.1

Grok Build 0.1 is a text and image-input model by xAI, available through the AgentSky API as xai/grok-build-0.1 at $1.10 per million input tokens and $2.20 per million output tokens, with a 256K context window.

xAI's lower-cost coding model for agentic software engineering and workflow tasks. This API model is separate from the Grok Build agent harness.

## Facts

- **Model id:** `xai/grok-build-0.1`
- **Maker:** xAI
- **Input modalities:** Text, Image
- **Context:** 256K
- **Released:** May 19, 2026
- **Aliases:** `xai/grok-build-0.1`, `grok-build-0.1`

## Pricing

USD per million tokens on the default plan. Signed-in pages show your own plan's price; every response carries the cost of that call in `usage.cost`.

| Input context (tokens) | Cache mode | Thinking | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|---|
| Up to 199,999 | default | default | $1.10 | $2.20 | $0.22 | — |
| Up to 256,000 | default | default | $2.20 | $4.40 | $0.44 | — |

## Use it

Anthropic wire base URL: `https://gateway.agentsky.dev`. OpenAI wire base URL: `https://gateway.agentsky.dev/v1`. Authenticate with an AgentSky API key (`ast_…`) and pass the model id.

### OpenAI SDK

```js
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.agentsky.dev/v1",
  apiKey: process.env.AGENTSKY_API_KEY, // ast_…
});

const completion = await client.chat.completions.create({
  model: "xai/grok-build-0.1",
  messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(completion.usage.cost); // USD, in the response
```

### Codex

```bash
export OPENAI_BASE_URL="https://gateway.agentsky.dev/v1"
export OPENAI_API_KEY="$AGENTSKY_API_KEY"

codex --model xai/grok-build-0.1
```

### OpenCode

```js
// opencode.json — then switch models any time with /models
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "agentsky": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "AgentSky",
      "options": {
        "baseURL": "https://gateway.agentsky.dev/v1",
        "apiKey": "{env:AGENTSKY_API_KEY}"
      },
      "models": { "xai/grok-build-0.1": {} }
    }
  }
}
```

## Questions

### What is Grok Build 0.1?

Grok Build 0.1 is a model from xAI. xAI's lower-cost coding model for agentic software engineering and workflow tasks. This API model is separate from the Grok Build agent harness.

### How much does Grok Build 0.1 cost?

$1.10 / $2.20 per million tokens at the prices shown, for input and output respectively. The exact price of every call comes back in the response as usage.cost, so you never have to compute it.

### What is the context length of Grok Build 0.1?

256K tokens. These are the limits listed for this model in the current AgentSky catalog.

### Which clients can call Grok Build 0.1?

Anything that speaks the OpenAI-compatible request format. Point the client's base URL at the gateway, use an AgentSky key, and pass xai/grok-build-0.1 as the model.

### How do I name Grok Build 0.1 in a request?

The gateway accepts xai/grok-build-0.1, grok-build-0.1. Any of them resolves to the same model, so an existing integration usually needs no change to its model string.

### Can Grok Build 0.1 read images?

Yes. Its listed input types are text, image. Include the image with your request; image input does not imply image generation.

### What output can Grok Build 0.1 produce?

The listed output types are text. This model returns text. Producing image, video or audio files requires a suitable tool or another model; it is not included in text generation.

### How should I plan a long prompt for Grok Build 0.1?

Plan your instructions, conversation history and source material around the 256K-token context limit, leaving room for the response. A larger window lets you supply more relevant material; it does not make unrelated content useful.

### What would 10,000 input tokens and 2,000 output tokens cost with Grok Build 0.1?

At the displayed input and output rates, the model-token subtotal is $0.0154. This example assumes uncached input and excludes additional pricing categories, tool calls and agent runtime. Actual usage determines the final charge.

### How is cached input priced for Grok Build 0.1?

The catalog lists $0.22 per million cache-read tokens. Repeating a prompt does not by itself guarantee a cache hit; only usage reported as cached receives that rate.

### Does the Grok Build 0.1 token price cover an entire agent task?

No. The model price covers the model usage described above. A task can also incur tool and runtime charges, and several model calls may be needed to complete it. Compare total task usage when evaluating cost.

### How do I use Grok Build 0.1 on AgentSky?

The composer above preselects Grok Build 0.1 for a compatible agent. Enter a concrete task, select any tools or connectors it needs, and send. Sign in if prompted; paid execution requires available credits.