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

# Grok Model Series Guide

> xAI Grok 4.x series (grok-4.5 / grok-4.3 / grok-4.20 / grok-build-0.1) on APIYI: OpenAI-compatible + Responses API dual endpoints, with web search / X search / code execution / MCP server-side tools verified working. Listed prices match xAI official.

Grok is xAI's flagship model family. The current generation (Grok 4.x) spans five product lines — flagship general-purpose, long-context standard, reasoning/non-reasoning variants, code-focused, and multi-agent collaboration — all available on APIYI. **xAI's official API is itself OpenAI-compatible** (Chat Completions + Responses API) with no separate proprietary protocol, so calling Grok through APIYI with the OpenAI SDK gives you the full feature set, including official server-side tools (web search, X search, code execution, Remote MCP).

This documentation group is based on a full hands-on test against the APIYI gateway on July 13, 2026 (UTC+8) — 56 request/response logs — so every capability boundary stated here is verified.

<Note>
  **🚀 Highlights**: grok-4.5 is xAI's newest flagship released on July 8, 2026 (knowledge cutoff February 2026), built for coding and agentic tasks; grok-4.3 and the grok-4.20 series offer a **1M-token context window**; the Responses API tools **web\_search / x\_search / code\_interpreter / MCP are all verified working on APIYI**, and X search is a capability unique to Grok.
</Note>

## Model Lineup

<CardGroup cols={3}>
  <Card title="grok-4.5" icon="trophy">
    **Flagship · Code & General**

    xAI's most intelligent model, 500K context, built for coding, agentic tasks, and knowledge work.
  </Card>

  <Card title="grok-4.3" icon="scale">
    **Standard Workhorse**

    1M context at roughly 60% of the flagship price — the balanced choice for everyday chat and mid-level reasoning.
  </Card>

  <Card title="grok-4.20 Variants" icon="split">
    **Reasoning / Non-Reasoning**

    `-reasoning` and `-non-reasoning` share the same price and 1M context; pick based on whether you want chain-of-thought.
  </Card>

  <Card title="grok-build-0.1" icon="code">
    **Code-Focused**

    256K context and the lowest price in the series — ideal for high-frequency code completion and light coding tasks.
  </Card>

  <Card title="grok-4.20-multi-agent-beta-0309" icon="users">
    **Multi-Agent Collaboration**

    Multiple agents work in parallel on complex research tasks. Special billing profile — see [Multi-Agent Model](/en/api-capabilities/grok/multi-agent).
  </Card>

  <Card title="More Capability Pages" icon="book-open">
    Chat/reasoning/vision: [Chat & Reasoning](/en/api-capabilities/grok/chat); live search: [Web & X Search](/en/api-capabilities/grok/web-search).
  </Card>
</CardGroup>

## Pricing

Listed prices match xAI's official pricing (verified item-by-item against the APIYI pricing API on 2026-07-13). APIYI's discount comes from [recharge promotions](/en/faq/recharge-promotions).

| Model ID                          | Context | Input              | Output             | Positioning                          |
| --------------------------------- | ------- | ------------------ | ------------------ | ------------------------------------ |
| `grok-4.5`                        | 500K    | \$2.00 / 1M tokens | \$6.00 / 1M tokens | Flagship: code / agents / general    |
| `grok-4.3`                        | 1M      | \$1.25 / 1M tokens | \$2.50 / 1M tokens | Standard workhorse                   |
| `grok-4.20-0309-reasoning`        | 1M      | \$1.25 / 1M tokens | \$2.50 / 1M tokens | Reasoning variant                    |
| `grok-4.20-0309-non-reasoning`    | 1M      | \$1.25 / 1M tokens | \$2.50 / 1M tokens | Non-reasoning (fast, low-cost)       |
| `grok-4.20-multi-agent-beta-0309` | 1M      | \$1.25 / 1M tokens | \$2.50 / 1M tokens | Multi-agent (billing amplification!) |
| `grok-build-0.1`                  | 256K    | \$1.00 / 1M tokens | \$2.00 / 1M tokens | Code-focused                         |

<Info>
  * The aliases `grok-code-fast` / `grok-code-fast-1` are also callable (connectivity verified); see the [model info page](/en/api-capabilities/model-info) for their pricing.
  * Cached input tokens are billed at a discounted rate. Grok prefix caching is **automatic — no configuration needed**; see [cache billing](/en/faq/cache-billing).
  * List prices match xAI official; stack [recharge promotions](/en/faq/recharge-promotions) for lower effective cost.
</Info>

## Verified Capability Matrix

Tested on 2026-07-13 (UTC+8) against the APIYI gateway (✅ verified working; — not covered, expected identical on the same architecture):

| Capability                           |     grok-4.5    |     grok-4.3    |     4.20-reasoning    | 4.20-non-reasoning |  grok-build-0.1 |  multi-agent  |
| ------------------------------------ | :-------------: | :-------------: | :-------------------: | :----------------: | :-------------: | :-----------: |
| Basic chat                           |        ✅        |        ✅        |           ✅           |          ✅         |        ✅        |       ✅       |
| Streaming (with usage)               |        ✅        |        ✅        |           ✅           |          ✅         |        ✅        |       ✅       |
| Chain-of-thought `reasoning_content` | ✅ on by default | ✅ on by default |           ✅           |   ❌ off by design  | ✅ on by default | internal only |
| `reasoning_effort` parameter         |        ✅        |        —        | ❌ explicitly rejected |          —         |        —        |       —       |
| Structured Outputs (json\_schema)    |        ✅        |        ✅        |           ✅           |          —         |        ✅        |       ✅       |
| Function calling / Tool Use          |        ✅        |        ✅        |           —           |          —         |        ✅        |       —       |
| Vision input (image understanding)   |        ✅        |        ✅        |           —           |          ✅         |        —        |       —       |
| Prompt caching (automatic)           |        ✅        |        ✅        |           ✅           |          ✅         |        ✅        |       ✅       |
| Responses API + server-side tools    |        ✅        |        —        |           —           |          —         |        —        |       —       |

## Endpoints

| Endpoint               | Method | Purpose                                                                                                      |
| ---------------------- | ------ | ------------------------------------------------------------------------------------------------------------ |
| `/v1/chat/completions` | `POST` | Chat / reasoning / function calling / structured outputs / vision (shared by all models; select via `model`) |
| `/v1/responses`        | `POST` | Responses API: web search, X search, code execution, Remote MCP and other server-side tools                  |

<Warning>
  **The following are NOT supported on APIYI** (verified — avoid these pitfalls):

  * **Legacy Completions (`/v1/completions`)**: rejected upstream — the entire Grok 4.x line is a reasoning architecture and does not support raw text completion at the official level
  * **Legacy live-search parameter `search_parameters`**: removed by xAI (verified 410). All live search goes through Responses API tools — see [Web & X Search](/en/api-capabilities/grok/web-search)
  * **Batch API / Files**: not routed by the gateway; not applicable to key-pool mode
  * **Deferred Completions (`deferred: true`)**: the parameter is **silently ignored** — the request executes synchronously and is billed normally. Do not rely on it
  * **Collections Search (RAG / file\_search)**: requires collections pre-built in the xAI console; not applicable to key-pool mode
  * **Context Compaction (`/v1/responses/compact`)**, **Priority Processing (`service_tier: "priority"` — falls back to default in testing)**, **WebSocket mode**, **mTLS authentication**: all unsupported
</Warning>

## Quick Start

<CodeGroup>
  ```bash cURL theme={null}
  curl -X POST "https://api.apiyi.com/v1/chat/completions" \
    -H "Authorization: Bearer sk-your-api-key" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "grok-4.5",
      "messages": [
        {"role": "user", "content": "Introduce yourself in one sentence"}
      ]
    }'
  ```

  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="sk-your-api-key",
      base_url="https://api.apiyi.com/v1"
  )

  resp = client.chat.completions.create(
      model="grok-4.5",
      messages=[{"role": "user", "content": "Introduce yourself in one sentence"}]
  )
  print(resp.choices[0].message.content)
  ```

  ```javascript Node.js theme={null}
  import OpenAI from 'openai';

  const client = new OpenAI({
    apiKey: 'sk-your-api-key',
    baseURL: 'https://api.apiyi.com/v1',
  });

  const resp = await client.chat.completions.create({
    model: 'grok-4.5',
    messages: [{ role: 'user', content: 'Introduce yourself in one sentence' }],
  });
  console.log(resp.choices[0].message.content);
  ```
</CodeGroup>

<Tip>
  **Which model to pick**: default to `grok-4.3` (1M context, balanced price); upgrade to `grok-4.5` for coding agents and complex tasks; use `grok-4.20-0309-non-reasoning` for fast, low-cost answers (no chain-of-thought, cheapest output); `grok-build-0.1` for high-frequency code completion; and only reach for the multi-agent model on complex research tasks (mind its billing amplification).
</Tip>

## Billing Note: Reasoning Tokens

`grok-4.5` / `grok-4.3` / `grok-build-0.1` **reason internally by default**: responses include `reasoning_content`, and reasoning tokens count toward output billing. In testing, a short answer showed just 30 visible tokens but billed 586 output tokens (556 of them reasoning). For cost-sensitive short Q\&A, switch to `grok-4.20-0309-non-reasoning`. Details in [Chat & Reasoning](/en/api-capabilities/grok/chat).

## FAQ

<AccordionGroup>
  <Accordion title="Does Grok have its own native API format?">
    No separate proprietary protocol. xAI's official REST API is OpenAI-compatible: `/v1/chat/completions` (chat) plus `/v1/responses` (Responses API and server-side tools). Point the OpenAI SDK at `https://api.apiyi.com/v1` and you get the full feature set — there is no "compatibility-mode downgrade".
  </Accordion>

  <Accordion title="How do I enable web search?">
    Use the Responses API: `tools: [{"type": "web_search"}]` (or `x_search`). The legacy `search_parameters` field on Chat Completions has been removed by xAI (verified 410) — do not use it. See [Web & X Search](/en/api-capabilities/grok/web-search).
  </Accordion>

  <Accordion title="The model introduces itself as Grok 4 — is my request hitting the wrong model?">
    This is normal. All Grok 4.x models self-identify simply as "Grok 4" (the multi-agent model calls itself Oppie) and won't report exact version numbers like 4.5 / 4.3. Verify identity via the `model` field in your request and the response, not the model's self-introduction.
  </Accordion>

  <Accordion title="Does caching need configuration?">
    No. Grok prefix caching is automatic; check hits via `usage.prompt_tokens_details.cached_tokens` (in testing, the second same-prefix request hit 2688/2735 tokens). The gateway runs in key-pool mode, so set reasonable expectations for hit rates — see [cache billing](/en/faq/cache-billing).
  </Accordion>

  <Accordion title="What happens if I exceed the context window?">
    A 400 error. Limits differ per model: grok-4.5 is 500K, grok-4.3 and the 4.20 series are 1M, grok-build-0.1 is 256K. Summarize, chunk, or use RAG retrieval for longer content.
  </Accordion>

  <Accordion title="Are failed requests billed?">
    4xx client errors (bad parameters / auth failures) are not billed; requests that successfully return tokens are billed by actual usage. Note that `deferred: true` is silently ignored — the request actually runs synchronously and is billed normally.
  </Accordion>
</AccordionGroup>

## Related Docs

<CardGroup cols={2}>
  <Card title="Chat & Reasoning" icon="message-square" href="/en/api-capabilities/grok/chat">
    Streaming, chain-of-thought, structured outputs, function calling, vision, caching
  </Card>

  <Card title="Web & X Search" icon="globe" href="/en/api-capabilities/grok/web-search">
    Hands-on with the Responses API web\_search / x\_search tools
  </Card>

  <Card title="Code Execution & MCP" icon="terminal" href="/en/api-capabilities/grok/code-execution-mcp">
    Server-side Python sandbox and Remote MCP integration
  </Card>

  <Card title="Multi-Agent Model" icon="users" href="/en/api-capabilities/grok/multi-agent">
    Capabilities and billing profile of the multi-agent model
  </Card>

  <Card title="Grok 4.5 Launch Deep-Dive" icon="newspaper" href="/en/news/grok-4-5-launch">
    In-depth look at xAI's newest flagship
  </Card>

  <Card title="Model Info" icon="database" href="/en/api-capabilities/model-info">
    All available models and groups
  </Card>
</CardGroup>